Best match

Most recent

Motorola

Back in the mid-2000s, Motorola scored a massive global hit with a high-style flip-phone called the Razr. The fashion icon was revived for the smartphone age in 2019, and now the company has out-flipped the competition with the Razr Plus.

https://www.bing.com/th?id=OVFT.Ir_qc9Ss1l3yJuKYy2AENi&pid=News

Motorola hopes you'll flip over the large cover screen on the Razr+

https://www.bing.com/th?id=ODF.a9T6RrkuK-92VuQVisWuZw&pid=news

New Atlas

Spotify

Barcelona's Sergi Ricart and Spotify's Marc Hazan look back on the campaign to evaluate whether the sponsorship has been a success so far.

https://www.bing.com/th?id=OVFT.Y6v1chwYyqW5jImwyO88aC&pid=News

Drake collabs, sneaker culture and Ronaldinho’s playlist… What Barcelona and Spotify have learned from one year of working together

https://www.bing.com/th?id=ODF.Y0KtYJTYZ3owkuWJRSWK7Q&pid=news

SportsPro

Powered by Web 3.0 technology – remember that ... are not necessarily putting up the same catalog that they have on all the major DSPs [like] Spotify or Apple Music. Instead, what tends to do really well on Audius is this grassroots sort of direct ...

Music’s biggest companies are determined to better monetize ‘superfans’ on streaming platforms. Audius is already doing it.

Traction

Music streaming giant Spotify previously launched its AI DJ feature in the U.S. and Canada, and now the U.K. and Ireland, as well. This AI-powered DJ personalizes its music recommendations for users based on generative AI and dynamic direction from Spotify's own Head of Cultural Partnerships,

https://www.bing.com/th?id=OVFT.wfTvMFsaYnyHLu5RGts7ri&pid=News

Spotify's AI DJ is Gaining Traction, Expanding into New Markets

Tech Zone 360

It is a systematic approach to identify and eliminate ... Spread the loveAs organizations continue to evolve and technology advances, there is a growing need to understand, model, and improve complex systems. Systems analysis is a structured approach to ...

How to Put a Song on Repeat on Spotify

thetechedvocate.org

Major

Android

The latest feature drop from Android brings new new emojis and widgets to phones and tablets and Spotify to WearOS.

Spotify gets a major upgrade on WearOS with Android’s latest feature drop

https://www.bing.com/th?id=ODF.l9XKvuAaphqgXpFEHtKlKg&pid=news

With the rising popularity of music streaming platforms, such as Spotify, music lovers have access to an extensive library of songs. However, limitations such as internet connectivity, device compatibility,

https://www.bing.com/th?id=OVFT.tM6zp4mAN1S4m6BscZPycS&pid=News

MuConvert Spotify Music Converter – Your Ultimate Solution to Getting All Your Spotify Content For Offline Entertainment

https://www.bing.com/th?id=ODF.WbwBhyLf0mt3sgNOM6CYtQ&pid=news

The Buffalo News

Advertising

Bill Simmons

In a podcast last week, Bill Simmons said ad reads could get a local element from artificial voices like his own. In this video, Travis Hoium covers what Simmons said and what it could mean for the stock.

https://www.bing.com/th?id=OVFT.4KOwzZ_8vI1Cu4rfxIO0ai&pid=News

According to Bill Simmons, Spotify's Advertising Is Getting an AI Boost

https://www.bing.com/th?id=ODF.4QjIDUvHz3Rc67mtMVQu7A&pid=news

The Motley Fool on MSN.com

host

With Spotify's AI DJ, the company trained an AI on a real person's voice -- that of its head of Cultural Partnerships and podcast host, Xavier “X” Jernigan. According to statements made by The Ringer founder Bill Simmons,

https://www.bing.com/th?id=OVFT.pivDK5DgutQYklYQwvGIri&pid=News

Spotify may use AI to make host-read podcast ads that sound like real people

https://www.bing.com/th?id=ODF.UM0amhg3WAObCEGqc4w_Cw&pid=news

Yahoo

Technology

Recommendation

Fintel reports that on May 23, 2023, Guggenheim maintained coverage of Spotify Technology (NYSE:SPOT) with a Buy recommendation. Analyst Price Forecast Suggests 6.00% Upside As of May 11, 2023, the average one-year price target for Spotify Technology is 157.

https://www.bing.com/th?id=OVFT.pZHPUzIwQlBgXBRNF-aipy&pid=News

Guggenheim Maintains Spotify Technology (SPOT) Buy Recommendation

https://www.bing.com/th?id=ODF.e8LTbsY6J5BsM-Feo9aqDw&pid=news

Fintel on MSN.com

Get the most recent info and news about Spotify Technology on HackerNoon, where 10k+ technologists publish stories for 4M+ monthly readers.

Spotify Technology S.A., together with its subsidiaries, provides audio streaming services worldwide. It operates through Premium and Ad-Supported segments. The Premium segment offers unlimited online and offline streaming access to its catalog of music and podcasts without commercial breaks to its subscribers. The Ad-Supported segment provides on-demand online access to its catalog of music and unlimited online access to the catalog of podcasts to its subscribers on their computers, tablets, and compatible mobile devices. The company also offers sales, marketing, contract research and development, and customer support services. As of December 31, 2021, its platform included 406 million monthly active users and 180 million premium subscribers in 184 countries and territories. The company was incorporated in 2006 and is based in Luxembourg, Luxembourg.

Spotify Technology

Write Code to Build Your Own Playlist and Throw Away Spotify

Introduction to Collecting Data Whether we appreciate it or not, everything we do in our daily lives is measurable by some metric. Therefore, data could be collected on every aspect of our daily lives. The advent of modern technology in day-to-day life has meant that there has been a mammoth increase in the amount of this kind of data being generated. In many cases, this kind of data has made huge changes in the way we think about and live our lives. Not only has this made our lives better but has allowed for major advancements in areas such as human behavior, conservationism, urban design, and public transport. I thought it was rather fitting in the spirit of this to use data to really explore some aspects of my life. I set myself two small challenges: 1. The first of which was to explore some of the data that was accessible to me that has been collected through my interactions with technology. All made possible thanks to , which gives individuals the right to request a copy of any of their personal data which are being ‘processed’. Article 15 of GDPR 2. Secondly to perform some very basic analysis of this data to find some fun, interesting, or useful insights into my life. My Data Sources The first of these missions was to find just some of the data that has already been generated for me. Very quickly I realised it was apparent that there were reams of different points that I could request access to and download, such as: – including posts or photos that I have shared, photos I am tagged in, posts I have liked, and groups I belong to amongst a whole host of other things. Facebook Data – which posts I have liked or commented on, who I have followed and who follows me, and what messages I have sent. Instagram Data – my Google advertising profile (allowing a peek into how I am seen online), locations that I have visited (the first of which I could find was from 2011), and a full log of all the YouTube videos I have watched. Google data – all my listening habits, how long I spent listening to various tracks, at what time, and on what day. Spotify data – Steps and distance walked or run (from mobile phone sensors), any connected Apple Watch data (BPM, temperature, etc.), and even mobility data about how ‘well’ I walk. Apple Health Data This is not an exhaustive list just possibly some of the platforms that are most widely used across the globe. The number of different data sources is likely to be endless and will only grow with time. However, for these purposes, I decided to look at what I could find out about my life from Spotify and Apple Health data. The Highlights · Since the 10th of November 2015 I have walked at least 15,340km or 20,577,340 steps. That’s roughly equivalent to walking from Cardiff to Queensland, Australia. · Climbed 44,471 flights of stairs, according to Apple Health this is one flight is worth 10ft. So aggregated (according to Apple’s website) this is 135km or the same as 161 and a half Burj Khalifa’s. · In the time period 13th February 2021 to 13th February 2022, I have listened to 55, 537 minutes of music or audio on Spotify. Compared to the Spotify annual reported amounts of 42,875 minutes and 25,6440 minutes in the calendar years 2021 and 2020. A YoY increase of 67.2% and 29.53% respectively. · On average listened to Spotify the most on a Thursday and listened to the most songs in February 2021. ·      Some other quick stats: o   Most songs on average were listened to at 19:00 o   Average number of songs listened to daily – 196 o   Listened to 2609 different artists o   Listened to 5322 different tracks Highlighted Graphs However, the purpose of this article was never to highlight the amount of data that big companies have collected on me or the ways in which they could process it to understand more about me. Instead, highlight the number of different ways that the same dataset can be represented to understand daily events and processes and draw attention to some inventive ways individuals and companies can use data to enhance our daily lives and progress society. Nobody is suggesting that this data analysis is one of those examples or that it has revealed much in the way of meaningful insight. It was all made possible thanks to legislation allowing individuals to have greater control over their own personal data as highlighted at the start of this article. I believe that legislation just like that will lead to an even greater data-sharing economy. One that incentives all participants to take part. Here are some examples: Monetisation over a current existing asset that is not utilised in this way. Better life outcomes and general day-to-day life Advancements in Science and Technology Whilst also balancing the privacy rights of those involved with this data collection, by adhering to the following: Total anonymization of data but instead different aggregations of this data to show trends. Ensuring robust licensing systems are in place to ensure that data is only used for the purposes it was collected for and proper access controls. Ensuring no bad actors obtain personally identifiable data for sinister purposes. I would invite you to think about some of the ways personal data from your own lives could be used to make better decision-making within the context of your own life. This was a super simple process so if you want to try this for yourself I’ve added some YouTube tutorials on how to download and request your personal data from third-party providers. This article was first published here.

What Apple And Spotify Know About Me

Lo que Apple y Spotify saben de mí

Ce qu'Apple et Spotify savent de moi

Apple और Spotify मेरे बारे में क्या जानते हैं

Apple と Spotify が私について知っていること

O que a Apple e o Spotify sabem sobre mim

Apple và Spotify biết gì về tôi

Apple 和 Spotify 对我的了解

Did You Know: Kubernetes Optimizes Audio-Streaming on Spotify! Spotify is an audio-streaming platform that was created with a vision to empower audio creators and endow listeners across the globe with a really immersive listening experience for all the customers across the globe. A customer-centric approach and a vision to empower creators have led to the exponential growth of the platform which has now grown to a superfluous number of 200 million monthly active users. Spotify, quite early, recognized the importance of containers and deploying microservices in a cloud-native environment. Consequently, they adopted a containerized environment pretty early and were amongst the few companies to even develop a home-grown platform for orchestrating the containers, which was named Helios. Adopting Kubernetes Meant Embracing Limitless Possibilities for Spotify Having adopted microservices and Docker quite early, Helios was a need-based innovation for managing the containerized environment for the Spotify team. However, the Spotify team soon realized the need to outgrow from this homegrown orchestration to Kubernetes. Helios only had limited features that could only be maintained by a small company at Spotify, contrary to this Kubernetes has many more functionalities that make it much more efficient than Helios and hence an obvious choice. Besides being laden with innumerable features Kubernetes also has an amazing community. To Spotify adopting Kubernetes was akin to adopting an orchestration tool that was not only already popular among many industry verticals but also could help their team get containers orchestrated more effectively, efficiently, and faster, and all of this, at a much lower cost than what the company had to incur with Helios. Also, there was a seamless migration from Helios to Kubernetes as Kubernetes could very effectively be used in conjunction with Helios, supporting migration until the platform became the only option for the full-fledged maintenance of the Spotify containers. Positive Impact of Adopting Kubernetes Migrating to Kubernetes required developing some core technological competencies. However, once the technological challenges were addressed and dealt with in 2019, and the company migrated to Kubernetes from their homegrown platform Helios, they experienced some amazing benefits in real-time business scenarios including the following: a)      The internal teams were able to considerably reduce the time spent on manual provisioning which meant that more time could be given to delivering features for Spotify. b)      The team was able to deploy some of its biggest services on Kubernetes, the likes that could handle as many as 10 million requests per second and cumulatively; the feature of Kubernetes proved simply amazing for the team. autoscaling Prior to adopting Kubernetes, deploying a new service for the team wasn’t this hassle-free. They had to at least wait for an hour to create a new service and would have to get an operational host for running the service in production. However, with Kubernetes the story was different. The same services could be deployed in seconds and minutes. c)       Kubernetes also helped improve the CPU utilization by 2 to 3 times approximately as it has the functionalities called bin-packing and multi-tenancy. d)      Kubernetes helped the autonomous engineering teams at Spotify work at a faster velocity and iterate more quickly even while working on different pieces of a project. Before switching to Kubernetes, Spotify since the year 2014 had been using microservices and Docker. The microservices were running across its fleet of Virtual Machines (VMs) and were containerized by leveraging Docker. The company used to manage and keep the data on-premises with the help of their home-grown container orchestration platform Helios before they migrated all the on-premise data to Google Cloud in the year 2016-17. Eventually, switching to Kubernetes proved to be a beneficial decision that offered innumerable advantages including accentuating the time of delivery of several services, leading to optimum business revenue. A substantial motive for the Spotify team to adopt Kubernetes was that the team wanted to contribute their subject-matter-expertise and influence to make the Kubernetes community prosper. Final Words: Takeaways From Spotify Use Case & the Road Ahead For Kubernetes With Kubernetes, not only the Spotify team was able to scale their topline operational metrics viz. lead time, deployment frequency, time to resolution, and operational load but were also able to get all the help to deploy the technology. The Kubernetes team was proactive in providing support and almost everybody was available to help the Spotify team with the technical know-how and expertise required while deploying a particular service. This served as a source of resurrection and motivation for the Spotify team to further scale-up their operational efficiency. The Spotify team leveraged several Kubernetes APIs and other extendable functionalities to aid and interface with their legacy infrastructure. The integrations were hassle-free and easy for the Spotify team. Because of saving so much time with Kubernetes, the Spotify team was able to experiment with solutions such as gRPC and Envoy. Kubernetes is becoming a go-to solution for companies with large development teams and complex IT needs. That's because software developers can use Kubernetes to automate the process of building and managing complex IT infrastructure. Kubernetes is already seeing adoption across many different industries and it will continue to grow as more governments and organizations come around to the benefits of its agility and automated operations. There are several other use cases that narrate the success story of Kubernetes across all industry verticals including media, publishing, audio streaming, and podcasting. These stories demonstrate the amazing possibilities that unfold when a team has the right API and enough time.

Why Spotify Migrated From Its Homegrown Orchestration Tool (Helios) to Kubernetes?

This is the experience of how my GitHub profile got me a job at Spotify. The key was my GitHub profile and the various repos I had worked on the years before. This post will be personal, and the key takeaway is the importance of a portfolio. It doesn't have to be a good portfolio (mine certainly wasn't). But having portfolio can be the difference between getting the job or not. a Spotify Interview Before Spotify, I worked as a software engineer at a different company. It was my first job after university and it was all right. I learned how software was being developed professionally which was fun and interesting. One day, I got an e-mail from Spotify and they were asking for applications for 3-month internships. I immediately sent them my CV. A couple of days later I received a phone call and I got called for an interview. The day of the interview is approaching and I'm starting to feel sick 😨. On the day of the interview, I had a fever, but I took some medicine and went there anyway. The interview did not go well. We talked and did some coding exercises on the board. I completely blacked out (partially because of the medicine). The last thing I said was " " and they said they would. Please, check out my GitHub profile After the interview, I was so disappointed in myself 😔. I returned home to my job, which now seemed boring and bleak. Call Back A few days passed and I got a phone call. It was the recruiter! He said they liked me and would like to offer me the internship! Wow, what a feeling! 😃 I accepted, and a few weeks later I quit my current job. My friends and colleagues were surprised I would quit my full-time job for a 3-month internship, but I didn't care. My two greatest passions in life are technology and music, and I was going to be working with both! 💻🎸 Internship Ends The deal with the internship was that if they liked me they would offer me a permanent job. The date when my internship was ending was quickly approaching. I was nervous, but I had learned so much and met a lot of people from different parts of the world so I was happy either way. We had a meeting and they said they would like to offer me a permanent job. Again, bliss! I felt such relief and of course, excitement! My GitHub Profile Later, I was talking to someone on my team about my interview. I told her how bad it went, and how surprised I was to still get the offer. She told me something like " ". Yeah, they told me it went bad. However, when we looked at your GitHub profile we saw that you can code. And that's why we wanted you My profile did not contain a lot; some HTML, CSS, and JavaScript websites I had built for fun and to learn. Before the interview, I looked through the code to make sure it looked nice and tidy. Conclusion I got an internship that later led to a permanent job at Spotify, thanks to my GitHub profile. I realized how crucial having portfolio is. It doesn't have to be the best, just something to show what you can do. This was 6 years ago. a I still work at Spotify, now as a Senior Software Engineer. It turned out to be an amazing place to work so I haven't found a good reason to leave. If I can do it, you can too!! 👊 Thanks for reading. Connect with me on , , or Twitter LinkedIn GitHub Also published at prplcode.dev

How I Got a Job at Spotify via my GitHub Profile

Spotify has faced calls for weeks to take action against Joe Rogan after accusations of promoting Covid-19 misinformation on his podcast, including hosting a guest banned from Twitter for spreading false information about Covid-19 vaccines. While Spotify declined to take action against Joe Rogan, it is committed to putting advisory warnings on podcast episodes about Covid-19. In this slogging thread, we discuss Joe Rogan's case and misinformation online. This Slogging thread by Mónica Freitas, Linh Smooke, Sara Pinto, Jack Boreham and Abeer occurred in slogging's official #podcasts channel, and has been edited for readability. Mónica Freitas Feb 7, 2022, 4:45 PM Spotify’s Joe Rogan Problem Isn’t Going Away https://www.nytimes.com/2022/01/31/technology/joe-rogan-spotify-controversy.html Mónica Freitas Feb 7, 2022, 4:47 PM "The audio giant has faced calls for weeks to take action against Joe Rogan, the mega-popular podcast host, after Mr. Rogan was accused of promoting Covid-19 misinformation on his show, including hosting a guest who had been for spreading false information about Covid-19 vaccines. This month, a group of hundreds of medical experts on Covid-19 misinformation, saying Mr. Rogan had a “concerning history” of promoting falsehoods about the virus." barred by Twitter urged Spotify to crack down Mónica Freitas Feb 7, 2022, 4:47 PM "Daniel Ek, Spotify’s chief executive, on Sunday, defending the company’s commitment to free expression and saying that “it is important to me that we don’t take on the position of being content censor.” And while Spotify declined to take action against Mr. Rogan, it committed to putting advisory warnings on podcast episodes about Covid-19, and directing listeners to a hub filled with authoritative health information." published the requisite blog post Mónica Freitas Feb 7, 2022, 4:49 PM How do you think this situation will turn out? And how should platforms handle the spread of misinformation and freedom of speech? 👀 1 Linh Smooke Feb 7, 2022, 4:52 PM (reacting so i will come back to this and offer a more thoughtful answer after this meeting!) 💚 1 Sara Pinto Feb 10, 2022, 11:01 AM Mónica Freitas, that's one of those sensitive topics that have to be approached with cautiousness. There's a thin line between spreading misinformation and freedom of speech, and I can see how this can become prejudicial. However, companies mostly want to make profits, so turning down a client because he talks about what he wishes in his podcast is a questionable choice. I get that this podcast may influence a lot of people, but if Spotify were to take him down, that would open start a lot of issues. Mónica Freitas Feb 10, 2022, 11:27 AM Sara Pinto, it's a tough subject indeed. One of the main backlash brought by Rogan's podcast is that many musicians are now trying to get their art removed from Spotify. This will also make the company lose money. So on that side, there's no way they can get out unscathed. Mónica Freitas Feb 10, 2022, 11:31 AM Sara Pinto, as for the spread of misinformation, it does worry me that such a big platform has no guidelines for it. I'd expect there to be some footnotes on how you transmit information to such a wide audience. And even though a podcast isn't necessarily a synonym of a reliable source of information, listeners are generally trusting of what they hear... So I get how this podcast got so many people believing misconceptions... It's a dangerous thing. Jack Boreham Feb 10, 2022, 11:40 AM In my opinion, I don't think there is a problem here. Freedom of speech is imperative for a fully functioning democracy. The reason why his show is so popular is that he invites people who have vastly different opinions and dissects their arguments. At the end of the day, it's all about personal judgement. If people want to believe what ex person said, then that's their problem. We live in a world where there is enough news out there for people to make informed decisions. No one should ever get their info from one place. Thus, in my view, this is just another case of people wanting to silence speech. It's stupid and makes the problem worse. 🔥 1 Sara Pinto Feb 11, 2022, 10:24 AM Mónica Freitas, seems like Spotify will end up losing money no matter the situation. I can see why the musicians are taking a stand, but what they are asking from the app... Sara Pinto Feb 11, 2022, 10:28 AM Mónica Freitas, I see, but where do you draw the line between "someone is spreading information" and "someone is giving their opinion even if wrong"? We can't forget that every fact nowadays is questionable, and rightfully so. As Jack Boreham said, we should get info from more than one source, and it's we should question what we heard. It is dangerous, but it all comes down to everyone's own way of judging. Mónica Freitas Feb 12, 2022, 11:51 AM Jack Boreham, that's very true. However, now there's a different dynamic with artists wanting their music removed from the platform. This puts a different pressure on Spotify. From what I've managed to find out, Spotify won't back down. Could this be the start of a crisis for the company or simply an episode that will soon fade away? Mónica Freitas Feb 12, 2022, 11:52 AM Sara Pinto, it's a tough spot to be in, no doubt. Spotify has to choose between its values and profits. Mónica Freitas Feb 12, 2022, 11:55 AM Sara Pinto, could it be that we're cuddling people when it comes to information? Abeer Feb 13, 2022, 6:29 AM Mónica Freitas, I can see Spotify taking a financial hit from this decision but I don’t think it’ll be big enough to make them change their mind. I’ve watched some episodes of The Joe Rogan Experience and I’ve enjoyed them even when I didn’t agree at all with what they were saying. Joe Rogan is a great interviewer that actually listens to his guests and interviews a diverse group of people. I’m sure that’s why a lot of people like him and trust his judgement. I think the root of the issue is regarding education and critical thinking. In my opinion, the majority of the public just echo what they hear from sources they like without scrutinizing it first. 🙏 1 Mónica Freitas Feb 14, 2022, 1:26 PM Abeer, that's true. I've never heard his podcast. What would say are the main topics he brings up for discussion? Also, why do you think the public has such a hard time sorting through the different sources of information? Are we just lazy when it comes to checking the facts? Jack Boreham Feb 15, 2022, 9:43 AM Mónica Freitas, I can see it fading away! I don't think it's worth the fight, to be honest. It will cost the artists far too much to remove their songs. Mónica Freitas Feb 15, 2022, 11:13 AM Jack Boreham, that's true, and it will be a short-lived scandal, minding that only a couple of artists have asked to remove their music from the platform. I'd be worried if there were masses of people canceling their subscriptions, but as it is... Sara Pinto Feb 16, 2022, 10:57 AM Mónica Freitas, maybe! I think we, as a community, should promote checking sources and info. Mónica Freitas Feb 16, 2022, 11:01 AM Sara Pinto, how much is it our job to incentivize people to check sources? Shouldn't it be an individual journey? Sara Pinto Feb 16, 2022, 10:56 PM Mónica Freitas, yes, it should be individual work, and I'm not trying to say there should be someone doing the work for others. But we still live in society, so I can't help but think that we should promote these activities. I think many people are naive, and we all know there's no better asset than being informed. Mónica Freitas Feb 17, 2022, 10:08 AM Sara Pinto, could it be that we, as a society, are too gullible? That we believe each other first before questioning sources, beliefs and other aspects that might be influencing our judgment? There's a sense of security to be able to simply trust another human...maybe that's why we fall so much into misinformation. Food for thought. Sara Pinto Feb 18, 2022, 7:00 PM Mónica Freitas, we can't forget that a few years ago there were fewer sources, so even if we worried about the credibility, there wasn't much we could do. And I think that leads to the fact that we don't do it as much now. Mónica Freitas Feb 21, 2022, 11:27 AM Sara Pinto, that's true too. I guess we're just lazy when it comes to information. Abeer Feb 22, 2022, 5:29 AM Mónica Freitas, he loves talking about working out, weed, and DMT. He likes to bring it back to topics he’s interested in as it makes it easier for him to be enthusiastic about it. He’ll also bring up recent events and news (or sometimes some personal stories) as a way to stir the conversation. As for the public being unable to sort through different sources of information, honestly, I don’t know. Maybe it really is laziness and no one wants to do the due diligence of fact-checking everything they hear. Or maybe it’s just too difficult of a barrier to figure out how to properly fact check things especially since there are so many BS sites online. I had to explain to my parents just yesterday that just because someone wrote something on a website that has “health” in the domain name doesn’t make it a fact. What I’m pretty sure of is that to some extent Confirmation Bias is at play which leads me to believe that some or maybe even many of the people who were “misinformed” by Joe Rogan would have probably taken those same stances regardless of whether or not they heard it on the Joe Rogan Experience. Mónica Freitas Feb 22, 2022, 6:34 PM Abeer, that seems interesting. I agree with you on that, I think the misinformed people would still fall into those same beliefs even if there was no Rogan. It's a sociological thing that I can't quite explain. Whether lazy, gullible or uninterested, those that don't work to check the facts, won't probably do it in the future.

Spotify’s Joe Rogan Problem isn’t Going Away

El problema de Joe Rogan de Spotify no va a desaparecer

Le problème Joe Rogan de Spotify ne disparaît pas

Spotify की जो रोगन समस्या दूर नहीं जा रही है

Spotify のジョー・ローガン問題は解決しない

O problema de Joe Rogan do Spotify não vai acabar

Vấn đề Joe Rogan của Spotify sẽ không diễn ra

Spotify 的乔·罗根问题不会消失

While “Tokenization” and NFTs have made strides in the art world and allowed some digital marketplace like to go mainstream it so far has had less success in the music industry. Decentralized streaming music services like have appeared but their scale and usage are still limited, and music is still sold to users as a fungible item online. Opensea Audius On the one hand, blockchains are only starting to resolve scalability and network latency issues. On the other hand, most of the music rights reside with legacy labels limiting the potential userbase, and thus networking effects of such decentralized services. Established music streaming services organizations like Spotify or YouTube Music currently benefit from substantial market power within their ecosystem. To paraphrase , as platform operators, they allocate rents between content publishers, users and advertisers who all rely on both their scale and their accumulated knowledge. Christian Catalini While Blockchain Technology can help such services better capitalize on the “New Content Economy” (Accenture.com) thanks to its ability to establish property rights at a finer level (Catalini) it also poses threats to the current balance of power within their ecosystem. Moreover, the rapidness at which the technology can be used to scale networks without the need for a traditional central intermediary when combined with the right “cryptoeconomics” also poses a competitive and existential threat (Catalini). Spotify or Youtube Music do not need to experiment with blockchain or “tokenomics” for funding purposes nor to build a network, but they could benefit from introducing a token in order to slowly change the way value is allocated in their ecosystem and to create new marketplaces. They should harness all their accumulated knowledge to do so. When launching a coin, Spotify and Co. should design incentives that promote the creation of “new content” without damaging their relationship with legacy music labels while leveraging their position as collectors of data to continue satisfying advertisers and curating their content. A way to do that would be to create two new “marketplaces” on their current music platform. One would focus on new artists with no current association with any labels and the other one on exclusive content from existing artists. On both marketplaces, content can be defined as music, exclusive audiovisuals, concert tickets, memorabilia, or any type of artist-related assets that can be tokenized. Artists can auction content or set it at a fixed price. The rationale in having 2 platforms is that the one with “known” artists will help in establishing a real benchmark value for the '“SPOTITUBEcoin” without the need for excessive liquidity. If “SPOTITUBE” was to list assets of unknown value with a token of unknown value, it would have to flush the market with liquidity and content to enable a price discovery. If a “U2” new exclusive release costs 1 “SPOTITUBEcoin” and the new song from an unknown artist cost 0.1 '“SPOTITUBEcoin” it gives users an idea of the potential value of the new artist thus creating a positive feedback loop. The rationale for not flushing the market with neither token liquidity nor content is both to leverage the potential diffusion effects that “New Early Adopters” can have on the technology when their need for feeling special is satisfied (Catalini & Tucker) but also to keep content scarce. Songs or content should only be available in a limited amount (at least some of them or for some time) to create value and further boost NEAs egos. As opposed to the classic streaming service everything that is purchased with “SPOTITUBEcoin” has a unique value and is not fungible. Artists or labels will also be able to issue equities in their next album or virtual concert (3LAU) and any other engagement activities between content providers and consumers will be encouraged to create a positive feedback loop. The coin should initially be issued and offered to current premium subscribers as they are more likely to be NEAs (course material). Non-redeemable large stakes should also be awarded (or sold at a discount) to current platform legacy content providers (music labels) to encourage their involvement in the new marketplace and slowly redefine their roles (course material). They will be the principal initial “stakers” (Ethereum.org). In time they will focus on creating and monetizing virtual events. Other users will either have to buy the coins or earn them through ad watching on the traditional streaming platform as with the “basic attention token”. (brave.com) so they only slowly gain access to the new marketplace. As in Brave, users will also be able to gift tokens to artists to support them. Finally, everyone will be able to redeem their “SPOTITUBEcoin” but large publishers like those publishing multiple artist or live VR concerts will have to keep part of their holdings “staked” to be able participate at such scale. Also published on BlockAdvisors .

On the Decentralization of Spotify and Similar Platforms

More consumed than ever, the digital audio streaming format that was an amateur investment and development has turned into a highly lucrative source of income for content creators and various businesses. According to the , the number of listeners globally has risen compared to 2019. The graph shows which countries have the most listeners in the last 12 months. Sweden came in first place with 47%, followed by Ireland and Brazil hosting more than 40%. Statista Global Consumer Survey Where Podcasts Are Most Popular With the increase of listeners, streaming music platforms have encouraged and invested in the new market of podcast creators, thus meeting the request of users and investors who demanded the immediate development of media with this market. Meanwhile, the platforms' unpreparedness about the method of publishing and making it available to their users allows a "backdoor" to exist that enables the publication of pirated content to be displayed freely. What Led to Piracy? What drove users to piracy was the desire to listen to content that they liked but would never be available on the platform. In a brief analysis of the explore, it is possible to find piracy of remixed songs, movie soundtracks, audio guides, and even pornographic videos. There are no checks on podcasts posted on platforms like and , a platform for creating and distributing podcasts at no cost. Spotify Anchor Besides the lack of verification, making content available and publishing it by web feeds facilitates piracy. In the case of Anchor, the podcaster records the episode, and once published, it is automatically distributed on all supported platforms from an . As a result, the violation spread to other streaming platforms that use the same publishing method. RSS feed Moreover, none of the platforms (Anchor and Spotify) simplified the means to make complaints about podcasts or programs that violate their content policies. To make any complaints about illegal podcasts, the user must search among the platforms' support options without any guidance from them about it. On Spotify, for example, users notice the absence of report buttons on podcasts, and this appears to be an oversight by the platform itself. The Other Side of Piracy Although the main reason for the backdoor reflects the availability of inappropriate content, there is an economic motive behind the whole story. In several fake podcasts, the presence of audio from paid content and a large portion of songs already available on the platform is notable. This issue reflects an alarming economic factor, especially in poorer countries or those that have suffered from the pandemic. In the case of Brazil, Spotify's monthly fee readjustment in April has caused piracy on the platform itself to increase. The premium functions available for podcasts (without restrictions or charges) attract users to pirate the platform. Downloading  and listening without random mode are functions that are available without payment. Possible Solutions The podcasting platforms could open complaint channels for podcasts, block feeds that disrespect the content policies, or report violations to the podcast creators. In addition, a deeper analysis of the feed content (name, image, title, and description) could aid in the detection of inappropriate content. Until these measures are taken, it will be impossible to eradicate piracy on any podcasting platform. But hopefully, taking these measures could decrease the number of copyright violations, avoiding future lawsuits.

Spotify's Backdoor: How Podcasts Could be the Platform's Downfall

As a long-time Spotify user, I love the end-of-year stats that Spotify surfaces each year. If you’re like me, you probably hate waiting till the end of each year just to see your top songs, artists, and genres. This is why I developed , a progressive web app that satisfies that curiosity! Spottr What Spottr is a PWA developed to surface your Spotify listening habits year-round rather than at the end of each year. Why The first main reason as stated above was the burning desire I had to know about how my listening habits have changed over time. The second reason was to rewrite this project again from scratch using Angular 10, Tailwind CSS, and push my design and front-end development skills. My first iteration was started back in 2018 with Angular 6, but I scrapped that since the project was not planned out properly. I am by no means an expert front-end developer (I mainly do back-end), but I wanted to see if I can produce a significantly better application just with more careful planning and research. One of the more interesting pieces of the app is the . This TTL cache was developed out of a need to keep the PWA snappy and keep data consumption low. If you think about the usage patterns of someone using Spotify, people may sometimes spend lots of time browsing different artists, albums, tracks, etc. which could result in a lot of extra round trips between the client and Spotify servers. This service was developed to provide a centralized mechanism to cache all HTTP requests. This allows for any other service to leverage the same caching strategy, resulting in faster development times. CachedHttpService The library also allows for a custom time limit to be set for the cached entries (the duration is known as TTL or time-to-live). Each request can have a unique TTL if you so desire. As a result, all other Angular services developed such as , , etc. all follow a repeatable and consistent pattern which reduces the chances for any silly bugs. ArtistService TrackService @Injectable()
export class MyService {
    // Inject the service here
    constructor(private http: CachedHttpService) {}
    
    getSomeData(id: string): Observable<GetSomeDataResponse> {
        const endpoint = new URL(ENDPOINTS.get(`get_some_data`));
        return this.http.get({
            url: endpoint.toString(),
            cacheMins: DEFAULT_CACHE_MINS,
        });
    }
    
    putSomeData(id: string, foo: Foo, bar: Bar): Observable<PutSomeDataResponse> {
        const endpoint = new URL(ENDPOINTS.get(`post_some_data`));
        const body: PutSomeDataRequest = {
            id,
            foo,
            bar,
        };
        return this.http.post({
            url: endpoint.toString(),
            body,
        });
    }
} This is just a brief overview of how it works, but I may write a more in-depth post on this in the future. On the UI side, this is my first project experimenting with Tailwind CSS which ended up being quite pleasant to use. A good chunk of the interface was built using . As a long-time Flexbox user, CSS Grid has proven to be an even more flexible way to lay out your components. CSS Grid Short self plug: If you’re looking for an extensive yet simple-to-learn SCSS framework, check out my project ! Cirrus How to Use Head over to . spottr.vercel.app Log in using your Spotify credentials. Browse Spottr! Current Features 📈 Top Stats View details for your top: Artists Tracks Genres Get data broken down for: Last 4 Weeks Last 6 Months All Time 🎶 Playlist Browse the playlists you follow or created. Get similar tracks for a given playlist. Export similar playlist to your Spotify account. 🎸 Track View track details including musical and audio features. Discover related tracks. 🎤 Artist View artist genres, follower count, and popularity. View artist's top tracks. Discover similar artists. Preview Tech Stack ⚡ - a platform for building mobile and desktop web applications. Angular 🎨 - Rapidly build modern websites without ever leaving your HTML. Tailwind 🎵 - for fetching Spotify data. Spotify API 📊 - Simple, clean and engaging HTML5 based JavaScript charts. Chart.js Planned Updates View recently played tracks. View top albums. Detailed beat analysis graph. Informational cards for each track and artist. Song lyrics. Thanks for reading! 💎 Thank you for taking the time to check out this post. For more content like this, head over to my actual . Feel free to reach out to me on and follow me on . blog LinkedIn Github

🎉 Introducing Spottr - Your Spotify Stats Year-Round

Thanks to artificial intelligence, machines now possess basic human skills: speak, write, see. Logically, the next evolving step is And music creation by AI is no exception. the process of creation. Unlike many other art forms, music and AI have known each other for a long time. Back in 1951, Alan Turing, an English mathematician, invented the machine that could generate simple melodies. In the 90-s, David Bowie was one of the first musicians to experiment with random lyrics generators, and Brian Eno wrote his album Generative Music 1 with the help of software engineering Koan. In 2016, Sony invented AI Flow Machines that also was a great help for musicians. The IIIiac Suite has become the first score composed by an electronic computer. Music Recommendation Artificial intelligence is not only a co-writer, sound engineer, or even a sound producer (like streaming services Spotify or Apple Music), it’s a huge influence on the music industry in general. In order to create accurate recommendations for you, . Spotify’s AI analyzes the listening history of the entire subscriber base against the songs in your heavy rotation AI compares the playlists you frequent to the playlists of other Spotify subscribers to locate users with tastes that are close to yours. After that, the AI finds song recommendations based on your own taste and on the music that users with similar tastes listen to. Both the ‘Discover Weekly’ and ‘Release Radar’ playlists on Spotify are actually algorithm-based features. These automatically generated weekly playlists are highly praised for their spot-on recommendations. There is no magic behind them, only powerful AI technology. Music Generation There are a lot of outstanding moments in the history of music co-creation by artificial intelligence and human artists. In 2017 musician Taryn Southern ; at the beginning of 2020, Björk worked with Microsoft to create . Sometimes AI even goes solo, like , a deep learning music composing service, that and became the first virtual composer recognized by music society. composed an entire album in collaboration with AI AI-generated music that changes with the weather AIVA released two albums While AI-generated music seems like a lazy and ‘weird new’ way of creation to some, David Bowie, one of the most unique and original musicians, used the AI-like script to generate the lyrics for his songs back in the 90s. Check out the clip of Bowie discussing his creative process utilizing Verbasizer . Verbasizer here However, AI music generation isn’t as trailblazing as it seems. Essentially, it just provides access to sophisticated yet easy-to-use tools and limitless tunes to play around with. Whether a musician or not, you can spark your creativity and have fun with AI-based services for music generation like , , and . With the help of AI, music analysis can be performed significantly faster and more accurately. Amper AIVA Boomy AI-based music analysis services can detect the most emotionally impactful track out of a playlist, album, or other song compilations. It helps musicians select the best track for a single release as well as aids playlist curators create the most soul-crushing playlists. The services also function as recommender systems for music streaming services due to their ability to detect similarities in BPM, mood, and style between tons of songs. Music Editing Before songs become available for our listening pleasure, they go through numerous editing steps. Many hours of attentive listening, making mixing and mastering choices, with each changing the final sound of a song or a record. It’s a lengthy process that requires a lot of resources from human specialists — another music-related task that can be accelerated and enhanced by artificial intelligence. , an AI-powered stem separation service, aids in deconstructing mixed songs into their constituent contributions, vocal and instrumental tracks. algorithms help to isolate each stem accurately and speed up the entire track splitting process to mere seconds. Separated vocal and instrumental stems can be used to create song covers, DJ mixes, karaoke backtracks, etc. LALAL.AI Machine learning is an AI-driven service users can utilize for music equalization. It automates the process of balancing out the specific frequencies of each track on an album or an EP to make the tracks complement each other. The EQ2 machine learning algorithm determines details that may pass the human ear, automatically corrects tonal imbalances, and increases the clarity of mixes. Smart: EQ2 and use machine learning to replicate the processes performed by mastering engineers. Both services utilize the technology to automate the final mix preparation process and provide almost instantaneous mastering results beyond the capabilities of any human mastering engineer. Though the majority of the process is automated, users still have control over their mixing preferences and sound influences. Izotope Landr Music Analysis Music analysis is a process of retrieving music data and breaking songs down into their characteristics. It helps musicians, labels, producers, publishers, and playlists curators organize and recommend music. With the help of AI, the analysis can be performed significantly faster and more accurately. The artificial music intelligence of listens to millions of songs in just minutes and simultaneously derives information from music to give each track specific characteristics. The service uses two types of analysis: gathers information about the rhythm, chord progression, harmony, etc. while deals with timbre, genre, and emotion of music. Cyanite symbolic analysis audio analysis The Difference Between Regular and AI/ML-Powered Services Creating algorithms (optimized models) from data is the most important aspect of machine learning. In contrast to systems that follow strict rules and perform tasks, in the same way, every time, machine learning algorithms improve with experience by learning from more input data. Computers are modelling different things, processes, and phenomena all the time. For example, any text editing software is a model of a typewriter, a digital calendar is a model of a paper calendar, Excel is a model of a checkered notebook. Although these models are significantly more advanced than their objects (real-life equivalents), they cannot be considered ‘intelligent’ since they do not learn and only repeat pre-programmed behaviour. Similarly, the stem separation quality provided by DAW plugins or any conventional software won’t be improving as you add more data, while the results of the stem splitting is going to get better over time because of the machine learning algorithms. LALAL.AI Also published here .

How AI Helps DJs, Artists Work with Sound (Beyond Spotify Algos)

In my previous story, I described the app that I . One of its features is to show a gallery of your favorite artists. Spotify compiles this from your library and listening habits. This is a nice visual representation but recently I went back to check something on the Spotify API and noticed that the retrieval of your takes an additional argument: time range.  This gave me an idea for a new feature to add to the app. How do your favorite artists change over time? This is the story of how I visualized my favorite artists from Spotify in a Plotly chart using Python. Additive Spotify Analyzer wrote favorite artists As in the previous article about working with audio features, we will also start with JSON files. In order to retrieve the favorite artists, we have to make three requests (long_term, medium_term and short_term time ranges) and we end up with three JSON files with the data. The files are already ordered by popularity. The hardest part is to visualize the data. How should it be represented? I took the data into a spreadsheet to play around and see what it looks like. In this spreadsheet, the left column is the long-term data, the middle column is medium-term and the right is the short-termed data. From this, we can see that there are very few artists that exist in all three-time frames. We have some that exist in two -ime frames but most exist in just one. (Katy Perry and Alicia Keys entries are from my SO when we were sharing my account... she now has her own... ;). First, I roughly decided to keep this format for a chart with three columns with the oldest data on the left and newest on the right but how do we go from a list of artist names to connecting the same artists across the three different time frames? In terms of charting, we have to think about a line in a 2D plane. We need one line per artist. Each line will have a maximum of 3 'x' values and a minimum of 1 (yes it will be a point then). An artist with 1 value exists only in one timeframe (we'll represent it as a diamond). An artist with 2 or 3 'x' values will form a line. For example 'At The Drive In' exists only in the long term time frame at position 16 so it can be represented by array [16, None, None] and 'Kaliber 44' only exists in a medium-term list so it will be represented by array [None, 7, None]. This transformation can be done in a quick loop. First, we initialize the None array to allow for each artist to appear only once. We create as many of these arrays as there are different artists. i, artistlist enumerate(topartists):
        topartistsranking.append([]) j, artist enumerate(artistlist):
            topartistsrankingM.setdefault(artist, [ , , ]) for in for in None None None Next, we need to attach the ranking for each artist in each time frame. (We also shift by one the ranking to avoid having the most popular artist at 0 positions instead of a more human-natural position 1 :) i range( ): j range( ):
            artist = topartists[j][i:i+ ] len(artist) > :
                a = topartistsrankingM.get(artist[ ])
                a[j] = i+ for in 50 for in 3 1 if 0 0 1 After this, we have one array per artist and we're ready to plot them. Having data that can be plotted is good but actually plotting it and visualizing is a different story. I started with a scatter plot but it was unreadable. Color is definitely useful in connecting the artists that have moved in popularity but with 96 artists it becomes too difficult to distinguish them. The color is also not enough to show the movement. I wanted a line linking the artists in different time frames. I went through many iterations of the chart. You can see some tests above on visualizing the data. Even though it looked cool to have all artists listed, it was a bit too busy so in the end, I decided to represent the artists which appear only in one timeframe with a marker and the artist which exists in more than one timeframe to have a name shown. The marker and lines most clearly conveyed the changing places of the artists and a hover-over effect easily shows what artist it is and what its fortunes were over time. To aid in identifying the fortunes of the artists I added the hover box that displays it. Here we can see a fall in popularity of 'Krypts' from 17th all-time position to 24. So if you're looking to find out your favorite artists over time, check out all of the code is available on . GitHub

Visualizing The Data: Spotify Data for Favorite Artists Over Time

There are many articles on analyzing Spotify data and many applications as well. Some are a one-time analysis on individual's music library and some are an app for a specific purpose. This app is different in that it does not do one thing. It is meant to grow and provide a place to add more analysis. This article is about how the audio features time series was created. More articles will be coming detailing other functionality. The app is currently deployed on Heroku and Render. To get the latest working address refer to the . project GitHub page Audio features time series This analysis looks best to those with a longer history of using Spotify as it shows data in a time series. A time series is, as the name suggests, data splayed over time. In this analysis, we use the song features provided by Spotify and map them over time to show whether our tastes have changed over time. In my case for example there is a slight decrease in the energy of the songs that I added in the recent 2 years vs the previous 4 years. (This I attribute to my SO :). In the app, after login we load data. There is a bit of processing but in the end, we end up with various JSON files. In this case, we will use tracks.json and audio_features.json. Both of these files have the same number of JSON objects and they're in the same order. In this analysis, we'll use these two data files to further transform them in order to plot them. We start with audio features. Below is an example of features for one track (we have 3868 tracks in our library). [
    { : , : , : , : , : , : , : , : , : , : , : , : , : , : , : , : , : , : }, "danceability" 0.517 "energy" 0.472 "key" 11 "loudness" -12.606 "mode" 1 "speechiness" 0.105 "acousticness" 0.191 "instrumentalness" 0.0946 "liveness" 0.105 "valence" 0.675 "tempo" 73.744 "type" "audio_features" "id" "2FUKNB0ArS2jVY73Ju3d2U" "uri" "spotify:track:2FUKNB0ArS2jVY73Ju3d2U" "track_href" "https://api.spotify.com/v1/tracks/2FUKNB0ArS2jVY73Ju3d2U" "analysis_url" "https://api.spotify.com/v1/audio-analysis/2FUKNB0ArS2jVY73Ju3d2U" "duration_ms" 404627 "time_signature" 4 Not all these are useful features for plotting. We'll only keep seven of them: ['danceability', 'energy', 'key', 'loudness', 'valence', 'speechiness', 'tempo'].  We also need to transpose this (in a simple loop) to have 7 arrays of 3868 data points long. Some of this data is already normalized but not all. We use sklearn.MinMaxScaler to do a quick transformation directly on the array. After this we now have our data array with data ready for plotting but it wouldn't be very much of a time series without timestamps. To get timestamps we turn to tracks. Each track has a date_added field and they're already sorted in our json file with the latest track added being on top. [
    { : , : {
                .. : , : , : , : , : , : }
    }, "added_at" "2020-11-16T11:08:53Z" "track" "name" "A Vast Filthy Prison" "popularity" 17 "preview_url" "https://p.scdn.co/mp3-preview/e60c4014418dfa75ec4201083e32f78831035c12?cid=47821343906643e3a7a156c5a3376c6d" "track_number" 10 "type" "track" "uri" "spotify:track:2FUKNB0ArS2jVY73Ju3d2U" We load tracks and again in a simple loop extract only what we will want to plot. We take the timestamp when it was added, artist and song name. We use this information as a hover over effect in the graph. At this time we have two arrays and we're ready to plot them. dataSeries contains the timestamps and song names used for hover effect dataToDisplay contains the data points for each music feature We create a loop where we add each feature as a separate trace on the same figure. We use Python's list comprehension to use in plotting where is the timestamp, is an array representing ith audio feature and is the artist and song title. dataSeries[:, 0] dataToDisplay[i] dataSeries[:, 1] Next we get the JSON representation of this graph and use Plotly JavaScript library. graphJSON = fig.to_json() This gives us the graph in its full glory. You can see the timestamps on the x axis and the data normalized on the y axis. We have 7 features for each of the 3868 tracks plotted. The full code is available on GitHub at https://github.com/dmossakowski/additive-spotify-analyzer

Spotify Audio Features Time Series in Additive Spotify Analyzer

We just open-sourced Klio — our framework for building smarter data pipelines for audio and other media processing. Based on Python and Apache Beam, helps our teams process Spotify’s massive catalog of music and podcasts, faster and more efficiently. We think Klio’s ease of use — and its ability to let anyone leverage modern cloud infrastructure and tooling — has the potential to unlock new possibilities in media and ML research everywhere, from big tech companies to universities and libraries. Klio But now we’re getting ahead of ourselves. What exactly is Klio and what does it do? Let’s start with the problem of audio itself. Audio is hard Really, sound is just wiggly air. At a basic level, every violin concerto, love song, dog bark, and knock-knock joke is the result of air compressing and vibrating, which we sense as it moves bones and hair in our ears. Sound is an invisible force that reaches us in ways that we can’t see, but can feel. And that’s what also makes audio so difficult for machines to parse. Humans can tell the difference between a swooning vocal, a danceable beat, and a buzzing bee. Can we teach machines to hear those differences, too? Machine listening, the field of research focused on getting computers to understand audio, combines expertise and methods from signal processing, music information retrieval, and machine learning — so that all those vibrations in the air result in data that makes a bit more sense for an engineer to work with. When encoded, compressed, and stored on a computer, you’re left with ones and zeroes packed into relatively large binary files. At a glance, a guitar solo can look just like a yodel. So, how do we begin to make sense of it all? And at scale? One is a popular podcast , one is acoustic guitar . It’s all just wiggly air. Software can help process the audio — identify voices, find beats per minute, analyze frequencies. But all at once? And 60+ million tracks at a time? One problem multiplied 60 million times Processing massive amounts of large binary files was a problem that was only getting bigger at Spotify. We’re adding about 40,000 songs a day and are processing our music catalog — about 60 million songs — on a regular basis, with multiple teams around the world doing work at the same time. Besides the problem of engineering that kind of scale and parallelization, we also wanted a way to tie the processing jobs more closely with the work our audio and ML research teams were doing. We were already building sophisticated data pipelines that supported AI and ML jobs using , a precursor to Klio. Scio Scio proved to be a flexible, scalable framework that any team could use to . build smarter data pipelines at scale By tying together large database queries, map-filter-reduce operations, natural language processing, and ML models, teams could create better, more personalized playlists, like Discover Weekly, Release Radar, and dozens of others. So, Scio created a platform for processing massive amounts of data about the audio. But what about processing the audio itself? A uniquely Spotify problem, a uniquely Spotify solution While processing metadata for the libraries of 299+ million users is impressive, it’s not the same as processing the content itself — those tens of millions of binary audio files that Spotify hosts and serves all over the world. On top of that, Java-based languages weren’t interfacing well with our Python-based research tools for audio and ML. We knew that if we could build data pipelines that supported large-scale audio processing, there were untold features and personalizations waiting to be unlocked. We just needed a framework that supported it — and that worked as well with our research tools as our engineering tools. In 2019, an ad hoc team of data engineers, ML researchers, and audio experts outlined the requirements for creating a framework designed especially for processing media. Scio was a model of success, but still just a starting point. This new framework would need to support: We wanted to transform audio, videos, images — all kinds of heavy-duty binary media files — in dozens of ways, with both streaming and batch processing. Large-file input/output: When you’re working with a dataset as large as the world’s music, as well as a burgeoning ecosystem of podcasts, you don’t want to have to redo your work over and over again. Scalability, reproducibility, efficiency: This translated into support for both Python (the lingua franca of both audio processing and ML) as well as non-Python dependencies (e.g., libsndfile, ffmpeg, etc.). Closer collaboration between researchers and engineers: In short, we needed a framework that could production-ize audio processing. This wasn’t just about creating data pipelines for media. It was about doing it at Spotify scale and with support for the latest audio and ML research. Let’s dig into that last requirement first. Researchers, engineers, and Python: The importance of speaking a common language Around this time, we noticed that both our researchers and engineers were beginning to get a little tired of the roadblocks preventing their audio work from getting adopted. Audio researchers were making promising breakthroughs, but the cost of getting new approaches integrated into shipping products was becoming increasingly high. As much as their counterparts in data and ML engineering wanted to help, those engineers were spending much of their time looking after several distinct, bespoke systems for production audio processing, all built and customized for individual teams. In other words, we had smart people all over the company working on audio, but our and engineers couldn’t work together, until most of the research was rewritten by the engineers. And even then, all that work and effort was siloed. world-class researchers The solution was simple: Python. It’s the native language of research and well-suited for the engineering problems at hand. Most importantly, allowing everyone to speak without a translation layer puts everyone in a position to focus on what they excel at. Audio and ML researchers get to focus on experimentation and building cutting-edge research tools. Engineers get to focus on building clean, reliable code. What is Klio? Klio is a framework for building smarter data pipelines for audio and other binary files, enabling you to production-ize media processing at scale. for a more ergonomic, Python-native experience for researchers and engineers Streamlined Apache Beam with support for top-down and bottom-up executions Open graph of job dependencies for managed resources and autoscaling production pipelines Integration with cloud processing engines for simplified development and easily  reproducible deployment Containerization of custom dependencies for continuous processing Batch and streaming pipelines Apache Beam under the hood, Klio in the driver’s seat It’s no surprise then that Klio is built on top of for Python, while also aiming to be a more Pythonic experience of Beam. Additionally, Klio offers several advantages over traditional Python Beam for media processing — providing a substantial reduction in boilerplate code (an average of 60%), a focus on heavy file I/O, and standards for connecting multiple streaming jobs together in a jobs dependency graph (with top-down and bottom-up execution). Apache Beam This allows teams to immediately focus on writing new pipelines, with the knowledge that they can easily be extended and connected later. This ease of use and streamlining of Apache Beam means we can get our state-of-the-art audio research into people’s hands and ears, faster. And while Klio offers this more opinionated way to use Apache Beam for common media processing use cases by default, it also allows the use of core Python Beam at any time if Klio’s opinions don’t fit your use case. Efficiency, efficiency, efficiency (DRY: Don’t Repeat Yourself) When we were developing Klio, we decided to test it by downsampling every track in Spotify’s 60-million song catalog — amounting to well over 100 million audio files in all (including multiple releases of the same song). Downsampling is often the first step of audio analysis, so it’s a great benchmark of what real-world performance might look like. Previously, the fastest we had accomplished this at Spotify was about three or four weeks. With Klio, we did it in six days, and reduced costs by four times. When you think about the number of songs in our catalog, and our quickly growing podcast library, Klio can have a tremendous impact on our teams and our business. With Klio’s streamlined framework, pipelines are more efficient and reliable. We can do in days what took weeks. And since jobs don’t have to be repeated (missing dependencies can be recursively created), you don’t have to run files through the whole pipeline again just to apply one more transformation at the end. You’ll find these kinds of optimizations throughout Klio’s implementation. Klio pipelines improve processing time and costs by avoiding duplicate work on already processed audio. And the framework is opinionated — encouraging engineers and researchers to write a pipeline focused on one thing, like finding the timestamps of all the beats to a song or measuring a song’s loudness. By creating reusable building blocks, Klio allows for researchers to build more easily on top of previous research and create graphs of pipelines, leading to features like infinite playlists optimized for your current mood, internal tools that help automate the review of new content, and powerful data that personalizes the Spotify experience for each user. Scale, reproducibility, and clouds. No infra team required. Klio can be run locally, but it really shines in the cloud — and is ready-made for it. In order to achieve the large-scale processing and reproducibility that we require at Spotify, Klio leverages the best parts of modern cloud infrastructures (like managed resources to autoscale production pipelines) and tooling (like containerization for easier deployments). Klio was designed to be cloud-agnostic, and the underlying Apache Beam project is designed to run workloads across any data workflow engine. Right now, it’s configured to work with Google Cloud Platform, but we welcome to help get Klio running on AWS, Azure, or another infrastructure. contributions : Current limitations to Beam Python prevent all of its features from being used on every engine, but we expect increased compatibility with Apache Flink and Apache Spark as Apache Beam extends its underlying compatibility with these engines. Preliminary work has also been done testing Klio on Amazon AWS and S3 using Klio’s Direct Runner. One thing to note We think this cloud integration (infrastructure as a service) can unlock production bottlenecks, as well as encourage experimentation. Engineering teams can rely on Klio to standardize media processing — using data processing and monitoring tools they’re already familiar with — rather than creating architectures from the ground up. Klio’s ability to autoscale production pipelines to handle variable workloads lets engineers focus on the next thing, rather than constantly tuning workloads. From Sing-Along to dolphin songs: Open and the great unknown Klio began as a proof of concept a little less than two years ago. It was invented out of necessity — to overcome challenges we were facing internally. But even from the very beginning, it was built with the intention of being free and open-source software. As we’ve seen with , our open platform for building developer portals, . We want to make the lives of engineers easier, so they can focus on building amazing things. So we’re excited to see not only how Klio can help others and advance audio/media research, but also what we can learn from others’ contributions and how Klio can evolve as a result. Backstage Spotify is committed to open source and developer experience Before and after Klio, Spotify has been doing this kind of large-scale audio analysis for nearly a decade, extracting and transforming tracks in our catalog on a weekly, daily, and streaming basis. Audio analysis algorithms power our for fingerprinting songs by their unique attributes (illustrated in this interactive article), in-house tools, like our automated content review screener; and market-specific features, like our Sing-Along feature in Japan — which as songs are uploaded to the catalog to create interactive versions that people can sing along with. Audio Features API New York Times separates the vocals from the instruments But as we saw when we open sourced Backstage, the open source community will come up with use cases we never dreamed of. And since Klio enables anyone to do this kind of heavy-duty media processing at scale (not just big tech companies), we’re particularly curious to see what academics and research institutions will build with it. ( ?) Dolphin speech, anyone So, thank you to the Klio team and to everyone who’s ever used Klio or contributed to its development over the years (including its sibling framework, Scio). And thank you to all those reading this right now and who will contribute to its development in the future. It’s a product that only Spotify could have built. But we’re even more proud now that it’s out there for the world to share. Now let’s . get started

Building the Klio Infrastructure to Support Audio Research at Spotify

Are you a person who likes to play different music based on various events or simply your mood? If yes, then Spotify is there to bring the best soundtracks in your life. As soon as you start using this service, you can explore many different features. In this post, I will provide you an introduction to Spotify and how it works. Do you know almost 140 million people are already using Spotify? Don't you wonder why? You should know that tons of people are using this music service for free, while others pay money to listen to music. Once you , I'll tell you some main differences between Free and Premium Spotify. become famous with Spotify What is Spotify? This digital music streaming service makes it simple for you to get quick access to millions of songs, videos, and podcasts from global artists. No matter what part of the world you belong to, it brings songs from your country's artists. Isn't that amazing? You can access this service from your smartphones and desktop as and when you need it. You can download the Spotify app on your smartphone and enjoy this service for free, but its paid version brings more amazing features. How Does Spotify Work? Every music lover finds it hard to stream his or her music online. First, you need to search for a track, then download it. Skip this hassle, make an account, and open in the worldwide music world. You can make an account through your email address or via Facebook account. I suggest you create an account through Facebook because this option offers you a chance to find your friends on Spotify and check their playlists. Create a Friend Circle - Getting connected to your buddies on an application would be a fantastic experience. Once you connect with them, you can share your favorite music tracks and find out what kind of songs your friends are listening to. Search Songs – You can search for songs by typing a song or start a search by adding artist names. You can also search for the movie name and find its songs. Once you start listening to a song, you can add all your favorite songs and make a playlist, which will stay active on your account and access it. Find the Right Music – The best thing is that you can find the right music for every moment of your life through Spotify. Whether you want a wedding song or some tracks for adding energy to your workout, there are tons of options to choose from. about Spotify Explore Collection- You can easily access the best songs collections of your friends, celebrities, and artists. Creating your own radio station based on your music preference is another fun element. Discover Podcasts - You can't only listen to songs but also podcasts. Whether you want to play a cooking podcast or have a desire to learn hunting through hunting podcasts, this digital streaming service will be available at your fingertips. Free Vs. Premium Spotify You can access this service either free or through Spotify Premium. There are some main differences between free and premium Spotify. Let's find out what these are. Download Music - When you subscribe to the premium Spotify service, you can download up to 10,000 songs on your device and access them through five different devices. This option isn't available through free Spotify;  you can't download any music. Ads – Free Spotify works like a radio; you need to listen to whatever plays there. If there is a commercial, you will hear it. However, you can listen to music nonstop with premium Spotify—no need to wait for ads to get over and then play your favorite music. On-Demand songs – You can't play whatever you like on free Spotify, but you can play songs on-demand as and when you want through . Spotify premium service Unlimited Skips – You can't skip more than six times in one hour while using the Free Spotify app, while the premium version lets you enjoy unlimited skips. Don't like a song, skip it and move to the next you want. Spotify Connect - If you subscribe to Spotify, then you can make the most of Spotify Connect. This feature allows you to connect Spotify to any Wi-Fi/Wireless device. That means you can join it to your TV speakers, Chromecast, Amazon Echo, PC, Google home, and other wireless devices. Once you create a connection, you can control music as your phone will work as a remote control. You can remotely play any song and change its volume. You can't get the Spotify Connect option on Spotify Free. How Spotify premium works If you want to avail of premium features, then you can subscribe to Spotify Premium. A single user can pay $9.99 per month. In case you want to enjoy this service alongside your partner, then buy Spotify Premium Duo for $12.99/month. When your whole family loves music, you should buy a family package for $14.99/month; it lets you access premium features on six separate family accounts. In case you are a student, you can enjoy a discounted rate of $4.99/month. Once you pay the premium cost, you get your account and play whatever you like whenever you like. How Spotify Free Works? If you don't want premium features like unlimited skips, no-ads interruptions, music download, and Spotify Connect, you can sign up for Spotify. Use your email address or Facebook account. Access its official site spotify.com from your desktop or download the Spotify application on your iOS or Android device and start digital music and podcast streaming. Final Thoughts Spotify lets you enter a digital music world where music, video, and podcast streaming are fun. You get connected with friends and get intelligent music and playlist recommendations based on your music history and preference. Once you are on this platform, you don't listen to the same music repeatedly because you find many similar songs and podcasts that match perfectly to your personality. Start with its free version, and you would soon like to pay a small fee to avail of its premium features.

What is Spotify And How Does It Work?

A law firm acting for Spotify has taken down a piece of Windows software that allows users to download and remove DRM from music tracks while skipping ads. XSpotify, which also carries an ad-blocking feature, is described as a tool that "steals" Spotify encryption keys in contravention of the anti-circumvention provisions of the DMCA. With more than 271 million users across 79 markets, Spotify is the most popular music streaming service in the world. Its 50 million song library is accessed by 124 million paying subscribers, who gain additional features such as an ad-free experience and the ability to download tracks to their own devices for offline listening. These tracks are encrypted so can’t be used outside the Spotify software, at least by conventional means. One tool that turns this business model on its head is Windows-based application XSpotify. The tool has gained popularity for a number of reasons, not least its ability to remove DRM from the tracks stored in Spotify’s extensive library and permanently download them for keeping on users’ machines. XSpotify has been quietly growing its userbase, offering track downloads from both free Spotify accounts (in 160 kb/s, 32-bit, 44100 Hz .ogg) and premium accounts (in 320 kb/s, 32-bit, 44100 Hz .ogg) while pulling down metadata such as artist, title, and album covers. Considering the above and its ability to block ads, it’s no surprise that Spotify eventually took legal action to tackle the spread of the tool. This week, Washington-based law firm Perkins Coie LLP sent a broad takedown notice to Github, where XSpotify was available for download, citing breaches of the DMCA by the app and its developer. “Copyrighted files on Spotify’s services are protected by encryption. Spotify uses a key to decrypt the copyrighted files so legitimate users can listen to the copyrighted files through the Spotify services. Spotify’s encryption system prevents users from listening to copyrighted works without Spotify’s decryption key,” the notice reads. “XSpotify states that it is a ‘DRM bypass’ that allows users to ‘Download all songs directly from Spotify servers.’ XSpotify’s technology circumvents Spotify’s encryption by stealing the Spotify key and using it in a way Spotify prohibits, namely, enabling users to access encrypted copyrighted content without authorization. “By providing technology that circumvents Spotify’s access controls, XSpotify violates 17 U.S.C. §§ 1201(a)(2),” the law firm . writes The section of US law cited by Spotify’s attorneys is clear. Among other things, it states that no person shall offer any technology to the public that is “primarily designed or produced for the purpose of circumventing a technological measure that effectively controls access to a work protected under this title.” In addition to removing the main XSpotify repository, Github was also ordered to delete almost 130 others that carried forks of the popular tool. At the time of writing, every repository reported by Spotify as infringing has been removed. Of course, XSpotify is still available for download from other locations but whether its developer will continue his work after this warning shot is yet to be seen. Originally published as “ Spotify Hits Windows Software That Downloads Tracks & Removes DRM ” with the Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0) license

Spotify Hits Windows Software That Downloads Tracks & Removes DRM

I read the news so you don't have to: Spotify has launched a co-listening product stream so that you can listen to the same song with anyone, anywhere, in-sync; big surprise: Facebook bought Giphy for the data; both Europe's budget airline Ryanair and Uber are laying off a bunch of people; and France and Germany are pushing for a $545bn coronavirus relief fund. 👾 what the tech Spotify is finally getting social. " Last week Spotify launched a global co-listening experiment with the aim to connect people through music. When you use Listening Together you get paired up with someone across the world to listen to the same song in sync, and you can travel around digitally to see what people in other countries are listening to. Spotify also recently launched group sessions so you can share DJ duties with your friends at a safe social distance." The real reason Facebook bought Giphy for $400 million "When Facebook confirmed that it had acquired Giphy last week for a cool $400 million, the reasons weren’t immediately apparent. Giphy has only the seeds of an advertising business, and GIFs aren’t a revolutionary advertising product. Mark Zuckerberg has a habit of knowing where the puck is going, but his company will have some real work ahead of it to make Giphy an advertising powerhouse. Still, the purchase may be worth it just for the insights it could yield about what web platforms people are visiting and what they’re sharing there." 😷 coronavirus coverage Coronavirus: France and Germany propose €500bn recovery fund " France and Germany are proposing a €500bn ($545bn; £448bn) European recovery fund to be distributed to EU countries worst affected by Covid-19 . In talks on Monday, French President Emmanuel Macron and German Chancellor Angela Merkel agreed that the funds should be provided as grants. The proposal represents a significant shift in Mrs Merkel's position. Mr Macron said it was a major step forward and was 'what the eurozone needs to remain united'." Ryanair to cut 3,000 jobs as coronavirus grounds flights " Ryanair is planning to cut 3,000 jobs and reduce staff pay by up to a fifth in response to the Covid-19 crisis, which has grounded flights. The no-frills airline said it was cutting 15% of its 20,000-strong workforce as it did not expect passenger numbers or pricing to return to pre-coronavirus levels until summer 2022 at the earliest. As part of a programme of sweeping cost cuts, Ryanair said it could close a number of bases across Europe until air travel recovers." Uber Cuts 3,000 More Jobs, Shuts 45 Offices in Coronavirus Crunch " Uber Technologies Inc. is cutting several thousand additional jobs, closing more than three dozen offices and re-evaluating big bets in areas ranging from freight to self-driving technology as Chief Executive Dara Khosrowshahi attempts to steer the ride-hailing giant through the coronavirus pandemic. Mr. Khosrowshahi announced the plans in an email to staff Monday, less than two weeks after the company said it would eliminate about 3,700 jobs and planned to save more than $1 billion in fixed costs." · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · all gifs are hacker noon originals

TODAY: Spotify 💚 Social · Y FB 💸 $400M on Giphy · Uber & Ryanair Cut Jobs   

Creating a Spotify Like Music Streaming App, Service or Website That Actually Boost Your Revenue

experience in the music industry comes from his early days of opening shows for artists like , , , Tyga, and various others. Adam Gonzalez’s Drake Trey Songz YG Now, he helps major records labels like Atlantic, Astrelworks, Hitco, APG, Epic, Interscope, and others with their marketing, using his strategies to build their developing artist fan bases from nothing to millions of fans all over the world. Adam Gonzalez is Sweetshop's new Senior Vice President of International Marketing and Co-Founder of Social IQ a marketing company that specializes in working with brands and developing artists for major record labels. According to Adam Gonzalez is one of Hollywood's top marketing and pr experts. Daily Press Adam Gonzalez says musicians frequently pivot onto making it to curated playlists, whether that’s editorial compilations like New Music Fridays, Caviar, Mint, Today’s Top Hits, Viva Latino!, Rock This, or user-generated playlists. Nonetheless, if your desire is to increase more streams, getting on algorithmic playlists like Release Radar and Discover Weekly can be much more powerful. Spotify’s Before we delve into Release Radar and Discover Weekly individually, here are a couple of pieces of advice that apply to get on both of these algorithm-based playlists: Adam Gonzalez says before we explore into Discover Weekly and Release Radar, here are a few bits of advice that cover getting on both of these algorithm-based playlists: RELEASE NEW MUSIC REGULARLY The more music you release, the more opportunities you have when it comes to landing on Spotify user’s Release Radar or Discover Weekly playlists. Be as it may, quality is more important than quantity, so if your output is high, make sure the definitive of each release is high too. MAINTAIN ALL ON-GOING PROMOTIONAL EFFORTS Concentrating completely on Spotify is a common mistake. If you become infatuated on Spotify playlists, you will miss out on other promotional opportunities, including social media ads, email marketing, and live shows, which all have their definite benefits and can certainly affect your performance on Spotify in their own way. HOW TO GET YOUR MUSIC ON SPOTIFY DISCOVER WEEKLY Each Spotify user receives their own unique Discover Weekly playlist every Friday morning. This playlist is based fully on that distinct user’s music tastes, and is not put together by Spotify’s editorial staff, but instead by an astute algorithm which analyses each individuals listening habits and reveals similar songs that may not have heard of in the past. How can you boost the chances of your music is included in a potential fan’s Discover Weekly? GET ADDED TO OTHER PLAYLISTS Spotify bases it’s Discover Weekly selections heavily around other playlists across the platform. It uses data across every playlist to determine tastes, artists similarities and what other listeners might enjoy, whether that’s a playlist with thousands of daily listeners, a user’s private playlist, or a public list with just a few followers. Every one of them counts. This is a quote from a Spotify executive and offers an explanation of how Discover Weekly is compiled. “We look at what you’ve been listening to. And what are the songs playing around these songs that you’ve been jamming on, but that we know you haven’t heard yet on Spotify. Let’s say you’ve been playing a song by The Killers and a song by Bruce Springsteen a lot. Algorithms look for how those songs are played and ordered in other Spotify users’ playlists. If it turns out that, when people play those songs together in their playlists, there’s another song sandwiched between them that someone has never heard before, that song will show up in your Discover Weekly.” MAKE HIT MUSIC & BUILD ENGAGEMENT If your music is not good you, you will have high skip-rates, listener engagement/retention and you won’t get picked up by Discover Weekly. On the other hand, it’s not all about how many streams you have. Typically a song with at least 20,000 streams has a good chance of making the cut, but more important metrics from the Spotify algorithm’s point of view include the portion of your tracks that are listened to all the way through, how many people save it, add it to their own playlists and share it on their socials, etc. This engagement is key. HOW TO GET MUSIC ON SPOTIFY RELEASE RADAR Despite Release Radar is still based on an algorithm, it’s a little less elaborate when it comes to understanding how and why music is subsumed. Similar to Discover Weekly, every weekly Release Radar playlist is unique to each user. Nevertheless rather than bringing up artist the user has yet to discover, it provides up to two hour’s worth of new releases from the artists they already follow or listen to on a regular basis. Here’s how to land on this playlist. GET FANS TO FOLLOW YOU ON SPOTIFY Your music will typically only appear on the Release playlists of the people who follow your artist profile, remarkably if you want to make sure they know about your latest track, ask them to follow you, rather than simply passively listening to your music on Spotify. Once you build up a good following, every time you release new music those fans will be notified via Release Radar. DRIVE LISTENERS TO SPOTIFY Gonzalez says if you have just released a new track, make sure to heavily incorporate Spotify into your promotional efforts. For instance, post links to your music on Spotify to social media and ask blogs that feature your tracks to embed them from Spotify. The more fans that visit your Spotify songs from “off-platform”, the better. Spotify’s algorithm-based playlists like Discover Weekly and Release Radar don’t just generate millions of streams for the artist, they generate Billions. Music fans tend to check these playlists first when searching for fresh music based on their specific tastes, or for a new track from their favorite artists- so don’t underestimate their promotional power.

Spotify's VP of Marketing Explains How To Get Your Music on Discover Weekly

Exactly one week ago today, I boarded a train heading North from Amsterdam to a town called Groningen, to attend the Eurosonic Music Festival (ESNS). ESNS is an incredible opportunity for both V Kewl industry folk who look like they just stepped off the set of V Cold plebbians in thermal underwear to discover hours worth of insanely great new music. Almost Famous and (it me) How ESNS Solved The Problem Of Spotify Personalization For Me , when I first discovered , I felt like their had looked into my soul and not only seen me, but me and wanted to me. And I was pretty smug about having listened to music from 66 of the world's 195 countries according to my . Just like everybody else Spotify Discover Weekly playlists loved hold Spotify 2019 Wrapped Story —I found my digital self unwittingly sellotaped to the other sheeple on the app's stream, wtf that means; at some point threatening to So Help Me Spotify quit music ~like, ~ if I heard another song. S ⁠ till "Indietronica" literally ever Little Dragon Suffice it to say, since attending ESNS last weekend, the lid on my Spotify recommends has blown right off. A Disclaimer Attending Music Festivals In The Tallest Country in The World , which is an impressive 1.5 inch (3.8 centimetres) increase on the Netherlands' average height in 1981. The average Dutchman is now 5.94 ft (1.81 metres) tall In Groningen, the charming and " " host host town of Eurosonic Festival in Northern Holland, they grow them even taller⁠—by about 1.2 inches (3 centimetres)—than those born in the South of this small country. gezellig I am, by most people's definition, a small person. Five-point-two feet (1.6 metres), to be exact. The acts I am going to list below made the fact that I mostly couldn't see them for shit entirely irrelevant. However! A Second Disclaimer Around My Qualifications in Music Journalism I don't have any. What's more, definitely probably, your taste is more refined than mine. If you're getting the same vibe, feel free to stop reading here and go search the ESNS playlists on Spotify instead. 👌 A Third Disclaimer Around The Logistics of ESNS The festival is plays out in 30+ venues scattered across the central town of Groningen, which looks like this: Some venues are far enough to justify biking too, but most are in walking distance of one another. Most are small. If you want to see the "big" names, you need to be queuing outside the venue at least a half hour before. Queuing is not my jam. I wondered aimlessly from act to act, and was rewarded with pretty mind-blowing sets at every stop. — — So without further delay here be the top 6 new artists who opened my Spotify algorithms to a whole new world. Charlotte Adigéry—Belguim 1. —London Via France 2. MADMADMAD 3. Cell7—Iceland 4. Miraa May—London 5. La colère—Switzerland 6. Meduza—Italy ("...definitely the last time these guys will be playing a venue this small.") substantiating claims / additional reading , Dutch people are tall AF but especially in Groningen Spotify's really hit the holy trinity of music recommendation models with their three-pronged approach of Collaborative Filtering (based on your and other users' behaviour, e.g. Netflix); Natural Language Processing (NLP) to analyze text, and MIT's Echo Nest breakthrough for analyzing audio— and your friends will be super impressed when you can explain it to them . . (Go on. Change my mind. ☕) ALL the best movies were made in the year 2000

Spotify Technology News on
HackerNoon and Around the Web

spotify.com

6617 employees

Since 2006

📉 Stock Prices

Spotify Technology Story Mentions

Articles Around the Web

Read More Tech Stories Related to #Spotify Technology

Spotify Technology News on HackerNoon and Around the Web