Voiceitt’s automatic speech recognition technology is designed to recognize atypical speech patterns

Voiceitt

Doing good in the world — and doing well financially For the bulk of human existence, innovation has occurred when a problem becomes so dire that it demands a solution. Long before we had accelerators, product ninjas, and tech gurus, we had people doing everyday things, running into everyday problems, and finding ingenious ways to solve those problems. The Chinese didn’t invent the compass to get rich; they wanted a more reliable way to navigate. Alexander Fleming had every right to hold his patent to Penicillin and become insanely wealthy, but he instead gave it up to the US and UK governments to save lives during WWII. The list goes on, but what’s recurrent in every tale is that the drive to solve a problem came first, and commercial application came second. What will be your contribution to the world? In a world where innovation, , and wealth are seemingly inseparable, it’s critical that we don’t start thinking these are linearly dependent. We can develop technology based on an idea, existing technology can spur further creativity, and new ideas can be instant financial juggernauts or slow-burning fires. technology The relationship between tech innovators and non-tech founders is indeed symbiotic. While non-tech founders may have a brilliant idea, if they’re not abreast of what new possibilities tech breakthroughs can bring, their idea may never come to fruition. Similarly, non-tech founders are always pushing developers to imagine new possibilities. Non-tech founders are driving development of new technologies Tomorrow’s great founders and CEOs are today’s field-specific experts. Lawyers who encounter cumbersome copyright management practices are turning to blockchain developers for smart contracts. Utilities are looking for more efficient ways to monitor the health of substations, and are spurring innovation in smart grid technologies. The examples are endless. Let’s look at a specific one, though, from the recent . Many of the pitches were based on Amazon’s AI and voice recognition technology Alexa, but were meant to address previously unsolved problems. Amazon Alexa Accelerator Demo Night Such was the case for , which was created to “make voice recognition technology truly accessible to everyone,” as the company writes, helping those with speech disabilities and communication barriers better connect with the world. Voiceitt Co-Founder and VP of Strategy has a BA in economics and received her MBA from Israel’s Yonsei University — a clear-cut non-tech founder. Her brilliant innovation grew from the desire to do good in the world, first and foremost. From there, she used her business management experience to attract funding despite the hurdles that come with social impact enterprises such as Voiceitt. Sara Smolley “We face a particular challenge when it comes to funding; traditional VCs may not see the larger market potential right away, and the traditional investor community may be wary of the double bottom line objectives (doing good while doing well financially) that is the hallmark of companies like ours,” Smolley for the Times of Israel. wrote in a piece “But those concerns have not prevented us from raising money. We have been able to raise funds through a creative combination of government grants, corporate cash prize competitions (like the Creator Awards), and investors who believe in our mission.” Smolley used her business savvy to take an idea, turn it into a product, and attract funding. Her story is one of dozens in which a technological solution to a human problem influences non-tech innovation, which then pushes the tech community to develop the proper tools, inspiring further innovation. It’s a fantastic cycle, but only if both the tech and non-tech communities are pulling their weight. They’re doing good in the world (and generating revenue) The drive to do good and solve global issues was highly prevalent at the Accelerator demo. , who has her MBA from Babson College in Boston and studied cognitive science and art history in her undergrad, founded . Alexa Bryanne Leeming Unruly This project, which is also a part of the Alexa/Techstars accelerator program along with Voiceitt, uses kinesthetic g to teach children the basics of coding. The system involves electronic programmable floor buttons, recess-style movement, tablet programs, and a combination of lights and sounds to make fun and improve retention. learnin learning Leeming’s Unruly is perhaps the purest example of why the tech community needs non-tech founders: Her idea alone could bring in a new generation of developers with more experience than any that came before, and they’ll be ready to find technological solutions to real-world problems. The way children learn is changing thanks to new tech developments. They know there’s no better time than now Moore’s Law says it all. The evolution of technology is infinite, but without application, breakthroughs will be irrelevant. It will be up to the non-tech community to bring forth the issues and possible solutions in their respective trades and occupations to make the most of these technological advancements. Fortunately, it has never been easier to transform an idea into a product. These founders are testament to the fact that you don’t need to be embedded in the world of tech to generate an earth-shaking tech innovation. You have the vision, and you have the management experience — don’t let a lack of IT knowledge keep you from pursuing your dream. The two non-tech founders listed above represent only a fraction of all entrepreneurs who have seen enormous success without any deep knowledge of IT. They may not originally have had the tech prowess, but they had the vision and they knew how to run a business. So, what’s stopping you from finding the same level of success?

Why Non-Tech Founders are Thriving at Amazon’s Alexa Accelerator

An Overview of the AWS Services needed for Chatbot Development AWS offers a range of services that can be used for chatbot development, including: - A service for building conversational interfaces into any application using voice and text. Amazon Lex - A service for converting text into lifelike speech. Amazon Polly - A service for transcribing speech to text. Amazon Transcribe - A cloud-based contact center service. Amazon Connect - A fully managed service for creating, deploying, and managing APIs. Amazon API Gateway Table of contents Designing the Chatbot Building the Chatbot with Amazon Lex Integrating the Chatbot with Amazon Polly and Amazon Transcribe Integrating Amazon Polly Integrating Amazon Transcribe Deploying the Chatbot with Amazon Connect and Amazon API Gateway Deploying the Chatbot with Amazon Connect Integrating the Chatbot with Amazon API Gateway Designing the Chatbot The in building an AI chatbot is designing the conversational flow. This involves that the chatbot will recognize and the responses it will provide. For example, the intent could be "Getweather", and an utterance could be "What's the weather like today?". The chatbot would recognize the intent and respond with the current weather information. first step defining the intents and utterances Once the intents and utterances have been defined, the is to create the chatbot using Amazon Lex. next step Building the Chatbot with Amazon Lex Amazon Lex is a service for building conversational interfaces into any voice and text application. To create a chatbot with Amazon Lex, follow these steps: Log in to the AWS Management Console and navigate the Amazon Lex service. Click the "Create" button to create a new chatbot. Give the chatbot a name and choose the language model. Define the chatbot's intents, utterances, and responses as described in the previous section. Test the chatbot by sending sample inputs and verifying that it returns the expected responses. Once the chatbot works as expected, publish it to make it available. Integrating the Chatbot with Amazon Polly and Amazon Transcribe Amazon Polly and Amazon Transcribe can be used to add voice and speech recognition capabilities to the chatbot. To integrate Amazon Polly, follow these steps: Log in to the AWS Management Console and navigate the Amazon Polly service. Create a new Polly voice, specifying the language and voice ID. Use the Amazon Polly API to convert text into speech. • To integrate Amazon Transcribe, follow these steps: Log in to the AWS Management Console and navigate the Amazon Transcribe service. Create a new transcription job, specifying the source audio file and the language of the audio. Use the Amazon Transcribe API to transcribe speech to text. Deploying the Chatbot with Amazon Connect and Amazon API Gateway Finally, the chatbot can be deployed using Amazon Connect and Amazon API Gateway. To deploy the chatbot, follow these steps: Log in to the AWS Management Console and navigate the Amazon Connect service. Create a new contact flow and specify the flow type (e.g. inbound, outbound, etc.). Add the chatbot as a contact flow block using the Amazon Lex bot. The next section will integrate Amazon Polly and Amazon Transcribe to add voice and speech recognition capabilities to our chatbot. Integrating Amazon Polly First, let's integrate Amazon Polly to convert text into speech. The following code shows an example of using the Amazon Polly API in Python to convert text into speech and save the result as an MP3 file. import boto3 polly = boto3.client('polly')

response = polly.synthesize_speech( Text='Hello, this is an example of using Amazon Polly to convert text to speech.', VoiceId='Joanna', OutputFormat='mp3' ) with open('polly.mp3', 'wb') as f: f.write(response['AudioStream'].read()) In the code, we first create a boto3 client for Amazon Polly. Then, we call the synthesize_speech method, passing in the text to be converted, the voice ID of the voice to use, and the desired output format. Finally, we write the resulting audio stream into an MP3 file. Integrating Amazon Transcribe Next, let's integrate Amazon Transcribe to transcribe speech to text. The following code shows an example of using the Amazon Transcribe API in Python to transcribe a speech audio file and print the resulting transcription. import boto3 transcribe = boto3.client('transcribe') 

response = transcribe.start_transcription_job( TranscriptionJobName='example_transcription_job', LanguageCode='en-US', MediaFormat='mp3', Media={ 'MediaFileUri': 'https://s3.amazonaws.com/example-bucket/example.mp3' } ) transcription_job_status = None while transcription_job_status != 'COMPLETED': response = transcribe.get_transcription_job(TranscriptionJobName='example_transcription_job') transcription_job_status = response['TranscriptionJob']['TranscriptionJobStatus'] transcription = transcribe.get_transcription_job(TranscriptionJobName='example_transcription_job')['TranscriptionJob']['Transcript']['TranscriptFileUri'] print(transcription) In the code, we first create a boto3 client for Amazon Transcribe. Then, we call the start_transcription_job method, passing in the name of the transcription job, the audio's language code, the audio's media format, and the audio file's location. We then use a while loop to poll the status of the transcription job, waiting until it has been completed. Finally, we retrieve the transcription from the transcription job and print it. We are deploying the Chatbot with Amazon Connect and Amazon API Gateway. In this section, we will deploy our chatbot using Amazon Connect and Amazon API Gateway. Deploying with Amazon Connect First, let's deploy our chatbot with Amazon Connect. To do this, follow these steps: Log in to the AWS Management Console and navigate to the Amazon Connect service. Create a new contact flow for the chatbot. Add a "Get Customer Input" block Integrating the Chatbot with Amazon Polly and Amazon Transcribe Amazon Polly and Amazon Transcribe can be used to add voice and speech recognition capabilities to the chatbot. , we can use the following code snippet in Python to convert text into speech: To integrate Amazon Polly import boto3 polly = boto3.client("polly") response = polly.synthesize_speech( Text="Hello, this is a sample text to be converted into speech using Amazon Polly.", VoiceId="Joanna", OutputFormat="mp3" ) file = open("sample.mp3", "wb") file.write(response['AudioStream'].read()) file. Close() , we can use the following code snippet in Python to transcribe speech to text: To integrate Amazon Transcribe import boto3 transcribe = boto3.client("transcribe") job_uri = "https://s3.amazonaws.com/your-bucket/sample.mp3"

transcribe.start_transcription_job( TranscriptionJobName="sample_transcription_job", Media={'MediaFileUri': job_uri}, MediaFormat='mp3', LanguageCode='en-US' ) while True: status = transcribe.get_transcription_job(TranscriptionJobName="sample_transcription_job") if status['TranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']: break print("Not ready yet...") print(status) Deploying the Chatbot with Amazon Connect and Amazon API Gateway. Finally, the chatbot can be deployed using Amazon Connect and Amazon API Gateway. Best Practices for Integrating and Deploying Chatbots on AWS: This section will discuss best practices for integrating and deploying chatbots on AWS, including handling error logs, performance management, and architecture design patterns. Handling Error Logs Logging and monitoring errors in your chatbot to identify and fix any issues quickly is essential. AWS offers diverse services to help with error logging and monitoring, including Amazon CloudWatch and AWS X-Ray. CloudWatch monitors and logs your AWS resources and applications, including chatbots. An X-Ray is a debugging tool that enables developers to analyze and debug distributed applications, including chatbots. Performance Management To ensure the optimal performance of your chatbot, monitoring and optimizing its performance is essential. Some best practices for performance management include: Optimizing the chatbot's response time by using efficient code and reducing the number of API calls. Scaling the chatbot to handle high traffic volumes using AWS Auto Scaling. Using Amazon CloudFront to cache responses and improve response times. Architecture Design Patterns Several architecture design patterns can be used to design and deploy chatbots on AWS. Some favored design patterns include: This pattern involves breaking down the chatbot into smaller, independent microservices that can be deployed and managed separately. Microservices Architecture: This pattern involves using AWS Lambda to run the chatbot code, eliminating the need for servers and reducing infrastructure costs. Serverless Architecture: This involves exposing the chatbot as a RESTful API using Amazon API Gateway, making it accessible from any application or device. API Gateway Pattern: Conclusion AWS offers a range of services that can be used for chatbot development and deployment, including Amazon Lex, Amazon Polly, Amazon Transcribe, Amazon Connect, and Amazon API Gateway. Following the best practices outlined above, you can design and deploy efficient, scalable, and reliable chatbots.

AWS Chatbot Magic: Building Conversational AI with AWS Services

Spoken Language Understanding SLU and Natural Language Understanding NLU aim to help machines understand human language. The main difference is the input data type. SLU deals with understanding speech, whereas NLU deals with understanding text. NLU is a part of SLU whether it’s trained independently or not. Research on NLU started in the 1960s: ’s Ph.D. dissertation Weizenbaum’s , a mock psychotherapist chatbot, and Winograd’s are the pioneer works in this space. SLU’s popularity started with the recent advances in speech recognition powered by deep learning. The query “spoken language” returns over 1000 studies on both and research publications websites. Bobrow ELIZA SHRDLU Amazon Microsoft Conventional SLU Approach The conventional SLU processes utterances in two steps - Speech-to-Text (STT) first, then NLU. Once STT transcribes the speech to text, NLU extracts meaning by processing the transcribed text. The performance relies on independently trained STT and NLU modules. If STT returns erroneous output, then it leads to incorrect NLU predictions. Hence machines cannot capture what humans say. Many voice applications, including voice assistants - Alexa, Siri, and Google use this approach. End-to-End SLU Approach The modern SLU uses an end-to-end model instead of two distinct components. Developers train STT and NLU jointly, resulting in higher accuracy. Picovoice calls this as it infers users’ intents directly from speech. Amazon calls it - Fusing ASR and NLU for SLU. Speech-to-Intent FANS Conventional SLU Approach vs. End-to-End SLU Approach The answer is It depends on the availability of corpora and information. If available, then the answer is modern end-to-end SLU. If not, then the conventional SLU. Text-based understanding (NLU) has been around longer than speech-based understanding (SLU). Thus, it has richer datasets. “it depends.” For domain-specific applications such as IVR systems, menu navigation on a website, or ordering food at a QSR, the modern end-to-end SLU is preferable. Nobody would discuss the meaning of life with a voice assistant while ordering a hamburger. For open-domain use cases such as voice assistants like Alexa, conventional -cascading SLU works better given the variety of topics they cover. One can discuss the meaning of life with Alexa - although there are better options. Top SLU and NLU engines in the market Free and Open-source SLU and NLU Engines: : Rasa is an open-source NLU engine that processes text inputs. The core software is free, and Rasa offers paid support and consulting services. Anyone can choose a speech-to-text service, and run Rasa on transcribed text. Rasa : Snips is an open-source SLU engine that uses the conventional method. Snips no longer maintains it after being acquired by Sonos. Yet the repo is still available on GitHub and used by developers. Snips : Wit.ai is a free platform and now requires a Facebook account after being acquired by Facebook. If one doesn’t (want to) have a Facebook account or deletes it, then they cannot use Wit. Wit.ai Top paid SLU and NLU Engines: : Google, after the API.ai acquisition, named it Dialogflow and offers both chatbot and voicebot tools under the same name. It uses the conventional approach. Dialogflow records and sends voice data to Google’s servers for transcription and then processes transcribed text. It charges based on usage. Dialogflow : Amazon’s Lex is an AWS offering. Like Dialogflow, Lex offers text and voice capabilities, uses the conventional approach, and transcribes speech and understanding separately in its cloud. It charges based on usage. Lex : Picovoice’s Rhino is an SLU engine that uses the end-to-end approach and infers intents and intent details . Rhino is voice-based and does not support text-based services. It charges based on the number of users and offers unlimited interactions per user. Rhino directly from speech

Spoken Language Understanding (SLU) vs. Natural Language Understanding (NLU)

In this article, I will be explaining how to cancel microphone noise on Linux. Prerequisites: PipeWire Arch Linux or Fedora The PipeWire is a multimedia framework built from scratch for very low latency processing of audio/video. One of the best features of Pipewire is that it provides a real-time capable plugin structure. The PipeWire daemon was built using this framework and is compatible with PulseAudio, JACK, ALSA, and GStreamer-based applications. Is PipeWire a requirement? No. You can configure this with PulseAudio. However, I have not tested it and verified it. By default, Fedora comes with PipeWire, and most other distributions include the PulseAudio. This article focuses on configuring the Noise canceling plugin with PipeWire and creating a Virtual Source to use as an input for any application, even web-based applications like Google Meet and Microsoft teams. The RNNoise — is the foundation of the Noice canceling plugin. a noise suppression library based on a recurrent neural network The Danylo Piliaiev develops and maintains the plugin, eliminating a wide range of noise origins like an airplane, construction, office/crowd, and computer fans. 1. Plugin Installation Arch Linux: To install the plugin on Arch Linux, you must use the . noise-suppression-for-voice AUR package Execute the following command to install the package using `yay` an . AUR helper $ yay -S noise-suppression-for-voice or you can install without an AUR helper with the following commands: $ sudo pacman -S git
$ git clone https://aur.archlinux.org/noise-suppression-for-voice.git
$ cd noise-suppression-for-voice
$ makepkg -si Fedora: The plugin can be installed on Fedora using the COPR repository. To configure this repository, enter the following command: $ sudo dnf copr enable ycollet/linuxmao To install the latest package, enter the following command: $ sudo dnf install ladspa-noise-suppression-for-voice Complete the above tasks to install the plugin binary into the location “ ”. /usr/lib/ladspa/librnnoise_ladspa.so 2. Create Filter chain for PipeWire A filter chain allows inserting an arbitrary graph of LADSPA (Linux Audio Developer’s Simple Plugin API) and built-in plugins in front of a sink or a source to create a new Virtual filtered sink/source. 2.1 Create a configuration directory to store filter chain configuration files. $ mkdir -p ~/.config/pipewire/ 2.2 Create a filter chain file “ input-filter-chain.conf . ” You can use any name you prefer, but make sure to use it throughout the configuration. $ vim ~/.config/pipewire/input-filter-chain.conf You can use this to create a configuration file for a PipeWire filter chain as below. Notice that the first filter graph node has a plugin property that points to the location. plugin = /usr/lib/ladspa/librnnoise_ladspa.so Paste the following content to the above file. # Noise canceling source
#
# start with pipewire -c filter-chain/input-filter-chain.conf
#

context.properties = {
  log.level        = 0
}

context.spa-libs = {
  audio.convert.* = audioconvert/libspa-audioconvert
  support.*       = support/libspa-support
}

context.modules = [
      {   name = libpipewire-module-rtkit
          args = {
            #nice.level   = -11
            #rt.prio      = 88
            #rt.time.soft = 200000
            #rt.time.hard = 200000
          }
          flags = [ ifexists nofail ]
      }
      {   name = libpipewire-module-protocol-native }
      {   name = libpipewire-module-client-node }
      {   name = libpipewire-module-adapter }
      {   name = libpipewire-module-filter-chain
          args = {
              node.name =  "rnnoise_source"
              node.description =  "Noise Canceling source"
              media.name =  "Noise Canceling source"
              filter.graph = {
                  nodes = [
                      {
                          type = ladspa
                          name = rnnoise
                          plugin = /usr/lib/ladspa/librnnoise_ladspa.so
                          label = noise_suppressor_stereo
                          control = {
                              "VAD Threshold (%)" 50.0
                          }
                      }
                ]
          }
          capture.props = {
              node.passive = true
        }
        playback.props = {
              media.class = Audio/Source
        }
    }
} 3. Configuration To load this filter chain to the PipeWire, we need to create a systemd service. The service we will be making as a systemd user instance and it will start at the first login. The systemd user instance is a per-user process and not per-session. 3.1 Create the systemd user configuration directory if it does not exist. $ mkdir -p ~/.config/systemd/user/ 3.2 Create a new systemd unit file. $ vim ~/.config/systemd/user/pipewire-input-filter-chain.service Make sure to: Replace the file name if you have used a different name for the filter chain configuration file. Replace the with your account username. <username> [Unit]

Description=PipeWire Input Filter Chain
After=pipewire.service
BindsTo=pipewire.service

[Service]
ExecStart=/usr/bin/pipewire -c /home/<username>/.config/pipewire/input-filter-chain.conf
Type=simple
Restart=on-failure

[Install] 
WantedBy=pipewire.service 3.3 Reload systemd user unit files. $ systemct --user daemon-reload 3.4 Enable the created systemd service. $ systemct --user enable pipewire-input-filter-chain.service Log out and log back in and check the sound control panel on your DE and you will see a new input source with the name “Noise canceling source”. If you do not see the new Virtual Source device, please check the systemd service’s status and rectify any errors in the configuration if the service fails to start. $ systemctl --user status pipewire-input-filter-chain.service 4. Finally, select the new audio source on applications. Google Meet Google meet provides a Noise cancellation option but I have deactivated it as the PipeWire plugin provided better voice quality compared to Google Meet's built-in method. For other applications, the configuration would be similar. Now you can make your meetings more effective and enjoy your podcasts and game streams without worrying about the background noise. References: Real-time Noise Suppression Plugin: https://github.com/werman/noise-suppression-for-voice AUR repository: https://aur.archlinux.org/packages/noise-suppression-for-voice/ Photo by on Sandra Tenschert Unsplash Also published . here

Enabling Instant Noise Cancellation on Linux

A Brief History of NLP Applications in the 21st Century “ ” Jarvis, you up? . For you, sir, always Tony Stark then goes on to give a series of commands to check and access his uber-cool Ironman suit. Jarvis even warns Mr. Stark that terabytes of calculations need to be done before an actual flight, only to be met with Tony’s cocky reply - “ ” Jarvis! Sometimes you gotta run before you can walk. Looks like a normal conversation with a personal assistant, doesn’t it? Except that Jarvis isn’t a human being but a smart AI assistant capable of holding seamless conversations and available at your service, always. If you want to reconstruct Jarvis in reality, Natural Language Processing (NLP) would be the first technology you would consider. A subfield of AI, NLP is a machine’s ability to understand human language in speech or text thereby narrowing the communication gap between man and machine. With enough virtual assistants like Siri and Cortana in the market already, are we ready to pull off a Jarvis? Let’s see how NLP was used over the decades and where it’s future course lies. Where did it all start? In his paper “Computing Machinery and Intelligence” published in 1950, Alan Turing poses a revolutionary question - “Can machines think?”. Though the 1940s saw glimpses of NLP in machine translation, the now-so-popular “ ” (also known as the imitation game), opened the possibilities of machines trying to comprehend the complex field of linguistics. Turing test To fulfill Turing’s criteria, a machine has to understand a human’s natural language in order to frame an intelligent human-like response. Many attempts were then initiated to pass the Turing test. ELIZA, SHRDLU, and PARRY were all precursors of interest in NLP. After a brief lull in NLP research, due to a halt in funding for NLP research by the Automatic Language Processing Advisory Committee (ALPAC) formed by the US government, natural language processing acquired a new dimension with the “statistical revolution” of the 1980s. To know the detailed history of NLP up to the 1990s, I suggest you go through an article by Dr. Hancox and another on dataversity . What we are more interested in here is the bloom in NLP since the 1980s, when application of statistical methods grew significantly. It is important to note that NLP may not necessarily be the backbone of all the technologies described in this post, but they do involve NLP tasks to a certain extent. The Era of Machine Translation You could call machine translation as the genesis of teaching machines our natural language. The ease with which Google Translate works now has a long history dating back to the 1930s when began to be filed for translating machines. patents Translations saw the light of day in 1954 when the was conducted by scientists to automatically translate more than 60 Russian sentences into English. In the , Statistical Machine Translation (SMT) stole the limelight off rule-based translation when researchers at IBM (Candide Project) worked on a large corpus of French and English texts found in the Canadian parliamentary debates reports, letting go of linguistic rules and calculated probabilities instead. Georgetown-IBM experiment late ’80s Meanwhile, the corpus-based translation or Example-based machine translation (EBMT) was also scrutinized by groups of researchers in Japan who worked with previously translated examples or corpora to translate new words. By , Systran’s machine translation was available in a few CompuServe chat forums and in 1997 one of the oldest online translators - BabelFish was launched by AltaVista (later taken over by Yahoo) that could do 36 pairs of language translation on a web browser. 1994 In 2001 syntax-based machine translation (translating syntactic units instead of words) was , followed by phrase-based machine translation between 2003 and 2005 that was later used to propel Google translate in 2006. Bing and Yandex launched their translators soon after in 2009 and 2011 respectively. proposed established While silent was carried out on using Recurrent Neural networks for MT, a decade since its inception, Google Translate a radical leap in commercial-scale translation by employing neural networks that were trained on very large datasets. research ushered Termed as the Google Neural Machine Translation system(GNMT), the engine behind Google Translate could confidently handle close to 10,000 language pairs in 2016. Ever since NMT came in the picture, hybrid approaches to translation are being experimented with to close the gaps in NMT with the benefits of phrasal or rule-based machine translation. Does this mail scream “SPAM”? The widespread use of E-mail as a form of digital communication to date comes with the classic problem of ham and spam. While IP blacklisting and email header inspection were initially used to identify spam, these methods when individually deployed were easily bypassed, thanks to IP and email spoofing. Thus arose the need for email content to be analyzed along with non-textual elements, signaling the entry of NLP to spot spam. In 1998, the was proposed followed by a commercially viable work on the same lines by Paul Graham ( ) in 2002. Bayesian approach to filtering junk e-Mail A Plan for Spam The Bayesian method, one of the earliest methods of statistical NLP, differed from usual text-based filters by its ability to automatically learn new words seen in probable spams and hence classified mails better with its expanding vocabulary. A word cloud of common words in spam Bayesian filters got better by scrutinizing mail header content, pairs of words, and phrases resulting in lower false positives and higher accuracy of spam identification and were implemented in many modern email clients. To further decrease the number of spams, Google in 2015 its usage of neural networks in its spam filters bringing the spam rate down to 0.1%. announced “Hey, Siri! What’s the weather like today?” An important movement in Natural Language Processing is IBM’s (1962) and later Harpy in the 1970s that stand as precursors for digital speech recognition. By the mid-1980s, the Hidden Markov Method (HMM) was found to be highly useful in modeling speech. Shoebox Though considerable success was shown by IBM’s Watson winning Jeopardy! In 2011, intelligent virtual assistants as we know them today gathered momentum when Apple out SIRI on iPhone 4S in the same year. And yes, Raj finally found the woman he can talk to in the 2012 Big Bang Theory series :) rolled Google Assistant (initially called Google Now) and Microsoft’s Cortana followed suite with Amazon introducing Alexa in 2014 sitting inside a smart speaker - Echo. To view a complete timeline of voice assistants, check out this cool infographic by voicebot.ai. AI voice assistants quickly found their way into a host of apps and devices, the google home for example, and Amazon selling over Alexa-enabled devices by Jan 2019. 100 million Chatterboxes to the rescue A close relative of virtual assistants is the AI-powered chatbots that carry out human-like conversations on messaging apps and online chats. The idea of machines trying to converse with humans was set off by chatbots like ELIZA(1966), PARRY (1972) and later by (1988) that even tried to crack jokes. With advancements in ML and Natural Language Processing, AI chatbots can now hold seamless conversations with users by understanding user intent and providing relevant inputs. Jabberwacky China-based company WeChat built a smart chatbot in 2009 but AI chatbots gained prominence in 2016 when Facebook it’s messenger platform to build chatbots and within 2 years active chatbots were developed on the platform. opened 300,000 Customer service has been immensely boosted by AI chatbots due to their 24/7 availability, the capability to address customer complaints and resolve simple questions. AI chatbots powered by NLP, are ready to take on of all customer service interactions worldwide by 2021. 15% Sniffing sentiments behind statements Going beyond mere text analysis, efforts were taken to identify the feelings behind highly unstructured content and their contextual significance. Early on classifying movie reviews found on the web as positive or negative using ML techniques (Naive Bayes, SVM, and MaxEnt) was done by Bo Pang et al in 2002. research A subsequent in 2004 by Bo Pang and Lillian Lee, discussed the radical effects of bringing “subjectivity” (how relevant is a particular word in voicing the author’s opinion) into classifying sentiments. These publications, along with Turney’s , kick-started a revolution of sorts in Natural Language Processing since growing language exchange on the web (social media, blogs, newsfeeds) was mined to understand people’s opinions. paper contributions Also commonly referred to as opinion mining, sentiment analysis was adopted by information giants like Thomson-Reuters who their inhouse NewsScope sentiment engine to measure news sentiment of thousands of companies for improved trading decisions. developed By 2009, Google implemented changes to its search engine based on research and patents filed by them that explored the concept of aspect-based sentiment analysis to summarize reviews based on sentiment. papers Soon in 2010, Twitter feeds were to gauge public opinion during the British elections, an example being a company called Linguamtics that scrutinized over 130,000 Twitter accounts. analyzed 2010 British election tweets analysis Though people were highly skeptical of the analysis and its outcomes, it got the tech world excited enough to it out on the 2012 US Presidential elections as well. In 2015, it was that industry leaders like Intel and IBM used sentiment analysis to decipher their employees’ emotions. try reported Emoticons, sarcasm, and language complexities challenge the field of sentiment analysis, yet companies have started rapidly investing in understanding public sentiment to amplify customer experience and glean consumer insights. So where’s NLP heading to these days? Apart from the major applications of NLP mentioned in this article, topic modeling, document summarization, and character recognition are a few other problems solved by natural language processing. The current Natural Language Processing scenario is strongly dominated by . Once driven by recurrent neural networks (RNN), deep learning-based NLP is now experimenting with that have been useful with sentiment analysis, question-answering systems, and machine translation to a certain extent. Deep learning models are also used to speed up or consolidate standard NLP tasks of POS tagging, parsing, and named-entity recognition. Deep learning Convolutional Neural Networks(CNN) proved Until transfer learning proves its stance, deep learning models require large data sets which we aggregate for you at . Xtract.io As the excitement around NLP mounts, maybe a decade from now JARVIS could be a reality and you can go and save the world, . perhaps

How Far Are We From a Real World Jarvis? 

Setup Docker I use a package manager called to install/uninstall software when I can. If you have chocolatey setup, just run the following command to install docker: chocolatey choco install docker-desktop Kitematic provides a visual interface to docker, so if you don't care much for the command line, I'd recommend installing that as well: choco install docker-kitematic Starting Docker After the installation has finished, log out then back in. Run docker desktop by pressing the Windows key and searching for docker desktop. Once docker is ready, you'll see the icon in the system tray stop animating and a login window will appear. The last step is to make sure Docker is working. Open a new PowerShell window and run the following command: docker run hello-world You should see output indicating that Docker is running. Run WordPress in Docker Now that Docker is set up on your system we can start WordPress. Since WordPress requires an instance of MySql running to store all of its data, we need to run two containers and connect them. We'll also want their data to persist if we stop the containers and restart them later. To accomplish this we create a docker-compose file, with volumes for each container. Save the following file as . docker-compose.yml version: "3.3" services: db: image: mysql:5.7 volumes: - db_data: /var/lib/mysql ports: - "3306:3306" restart: always environment: MYSQL_ROOT_PASSWORD: somewordpress MYSQL_DATABASE: wordpress MYSQL_USER: wordpress MYSQL_PASSWORD: wordpress wordpress: depends_on: - db image: wordpress:latest volumes: - wordpress: /var/www/html ports: - "8000:80" restart: always environment: WORDPRESS_DB_HOST: db:3306 WORDPRESS_DB_USER: wordpress WORDPRESS_DB_PASSWORD: wordpress WORDPRESS_DB_NAME: wordpress volumes: db_data: {} wordpress: {} Open a shell in the directory where you saved the docker-compose file and run . After a few minutes, you'll have WordPress running on your machine. docker-compose up -d Running WordPress Install Before you can start writing plugins for WordPress, you need to run through the setup pages on your new server. Browse to and follow the instructions. http://localhost:8000/wp-admin/install.php Creating a Plug-in To create a plugin, you need to add a folder in WordPress' directory. To find the root directory, open kitematic by clicking on the docker icon in the system tray and selecting from the menu. plugins kitematic Now select the WordPress container on the left side of the window, and click under the list of volumes on the right side. /var/www/html This will open Windows Explorer with the folder selected. Open it, then browse to . Create a new folder called first-plugin then open it. Create a file called inside the new folder and paste the following code into it: html wp-content->plugins index.php <?php /**
* Plugin Name: First Plugin
* Plugin URI: https://voiceify.io
* Description: Your very first plugin!
* Version: 1.0
* Author: Ben Force
* Author URI: https://twitter.com/theBenForce
* License: GPLv2 or later
**/ Save the file and browse to , you should your plugin in the list. http://localhost:8000/wp-admin/plugins.php I hope this tutorial has given you a good starting point that's easier than installing a PHP server and MySQL. Let me know if you have any suggestions or questions.

How To Run Wordpress In Docker

In this pandemic, a lot has changed with work culture. Something we can’t get rid of yet is . While at one of those meetings, I got curious about the and after some search came to know what our browsers are capable of (inbuilt browser APIs). Remote Meetings Google meeting platform So, I planned to develop a free simple recorder that supports Audio, Video, and Screen Recording available at http://recorder.dhruv479.dev To proceed further, you should be acquainted with some terms: The MediaRecorder interface of the provides functionality to easily record media MediaRecorder: MediaStream API ref: MDN The MediaDevices interface provides access to connected media input devices like cameras and microphones, as well as screen-sharing MediaDevices: ref: MDN Ok, ready to roll? let’s add some code! At first, we will write a function that intakes the stream and mimeType, collect the data chunks and then enable downloading the file on the local machine from the browser. Recording Handler: handleRecord = { recordedChunks = [];
  stopped = ; mediaRecorder = MediaRecorder(stream);

  mediaRecorder.ondataavailable = { (e.data.size > ) {
      recordedChunks.push(e.data);
    } (shouldStop === && stopped === ) {
      mediaRecorder.stop();
      stopped = ;
    }
  };
  mediaRecorder.onstop = { blob = Blob(recordedChunks, { : mimeType
    });
    recordedChunks = [] filename = .prompt( ); downloadLink.href = URL.createObjectURL(blob); downloadLink.download = ; stopRecord();
  };

  mediaRecorder.start( ); }; const ( ) function {stream, mimeType} // to collect stream chunks let false const new ( ) function e if 0 // shouldStop => forceStop by user if true false true ( ) function const new type const window 'Enter file name' // input filename from user for download // create download link for the file ` .webm` ${filename} // naming the file with user provided name 200 // here 200ms is interval of chunk collection First, create a MediaRecorder instance with the input stream. Then, add events for ondataavailable (when data comes in-stream) and onstop (when the stream stops). After chunk is available, it is pushed in the array and after the stop event, all the chunks are put together to form a specifying the mimeType. Blob Later, URL is created for the blob object and can be downloaded from the browser. Going forward, we will write a function to invoke the audio recording that further calls handleRecord with the required parameters. Audio Recorder: { mimeType = ;
  shouldStop = ; stream = navigator.mediaDevices.getUserMedia({ : });
  handleRecord({stream, mimeType})
} async ( ) function recordAudio const 'audio/webm' false const await audio true Here, we will use mediaDevices.getUserMedia to get access to resources on the user’s machine. After calling this,  we will get a prompt asking for permission in the browser and after confirmation, we can access those resources. Also, we can pass additional parameters to the constraints like audio: { echoCancellation: true } which reduces the sound echo. Similar to Audio Recording, we need to add video in the parameter of the function. Video Recorder: getUserMedia { mimeType = ;
  shouldStop = ; constraints = { : , : ,
  }; stream = navigator.mediaDevices.getUserMedia(constraints);
  handleRecord({stream, mimeType})
} async ( ) function recordVideo const 'video/webm' false const audio true video true const await After adding video constraint in getUserMedia, you will get an additional prompt to camera permission and after the confirmation, guess what, we can access the camera stream. Also, additional params can be passed to video such as: video: { width: {min: 640}, height: {min: 480}} Amongst all, this is the most interesting, as the display stream is provided by getDisplayMedia, and the audio is provided by getUserMedia. So, we need to merge different streams here if need an audio background for the screen record. Screen Recorder: { mimeType = ;
  shouldStop = ; constraints = { : }; displayStream = navigator.mediaDevices.getDisplayMedia({ : , : }); voiceStream = navigator.mediaDevices.getUserMedia({ : , : }); tracks = [...displayStream.getTracks(), ...voiceStream.getAudioTracks()] stream = MediaStream(tracks);
  handleRecord({stream, mimeType})
} async ( ) function recordScreen const 'video/webm' false const video true const await video true audio true // voiceStream for recording voice with screen recording const await audio true video false let const new We merged the different streams to create a new stream and passed it to the handleRecord function. Here also, we can add more specific constraints as per the need. Constraints passed to capture media can be more specific like resolution, echo, cursor instead of true/false. Conclusion Voila, well the JavaScript part is done 😁. We just need to add some basic HTML to invoke those functions, stop recording, and of course, download the file. Here is a reference to the complete code: https://github.com/dhruv479/recorder/blob/master/index.html Also published at https://dhruv479.medium.com/583584dd3c75

Here's How I Built a Video, Audio, and Screen Recorder Web App with JavaScript

How big will voice-based interfaces become in 2020, and how will we use voice differently? This question is on the minds of behavioralists, technologists, and businesses everywhere as we all adapt to / create a new normal. At the outset of 2020, voice was growing at a predictably robust rate. A consumer conducted by Voicebot showed that 87.7 million Americans had adopted a smart speaker by January 2020, up 32 percent year over year. Also, the number of in-car voice assistant users rose 13.7 percent to 129.7 million. survey And then COVID-19 hit, upending everything. Weeks after President Trump issued a national state of emergency on March 13, a picture is emerging of how people are relying on voice. On April 27, The Wall Street Journal, citing from Euromonitor International, published a wide-ranging analysis of how consumer behaviors are changing during the pandemic. One of the major trends: people becoming more receptive to the person-machine interface, including voice: research Consumers have suddenly become far more comfortable with robots and other types of artificial intelligence performing jobs traditionally done by humans. Euromonitor earlier this year noted that consumers were buying more AI-enabled home appliances and virtual assistants, like Amazon.com Inc.’s Alexa. But now, such devices have a new draw, says [Alison Angus, head of Euromonitor’s lifestyle research]. “Voice-control technology limits the need to touch surfaces so much, so that’s why they are appealing,” she says. Robotic innovation is further driven by businesses investing in technologies that offer no-contact services and deliveries. “This pandemic could well propel robots into the mainstream, moving them from novelty to essential,” says Ms. Angus. “In fact, it could be a situation where tech actually has to catch up.” This finding aligns with a blog post I wrote in April, “ .” I wrote, “ . . . using smart voice assistants to manage our lives – to do everything from ordering products to getting information – looks to be a less risky behavior from a health standpoint than an interface that requires touching a screen or clicking on a keyboard.” Mindful Innovation in a New World Are people using voice during this global pandemic? Yes. That’s what research by Edison Research and NPR : reveals Voice assistant use frequency is indeed on the rise. What are people using voice to do during the pandemic? The Euromonitor research didn’t say. But a little digging reveals a few interesting uses: Cooking: Allrecipes Alexa skill sessions are up 67 percent over the past 30 days. Unique users has risen 80 percent during the same period with first-time users up 45 percent. This data makes perfect sense as people shelter in place and look for more things to do in the home. Companionship: as CNet reports, seniors in a California senior living center living in isolation are using Alexa to stay connected with each other. According to Edison Research Senior Vice President Tom Webster, overall, smart speakers are also becoming a lifeline for information. “With tens of millions of Americans no longer commuting, smart speakers are becoming even more important as a conduit for news and information,” he said in an article, “and this increased usage and facility with voice assistants will likely increase demand for this technology in vehicles once our commutes resume.” How might uses of voice assistants change throughout the year? Possibilities include: , especially now that the major voice assistants have made it possible for people to self-check for COVID-19 symptoms. Checking up on our own health Newsweek that the majority of Americans will hit a mental breaking point if stay-at-home orders continue to June. Meanwhile, The Wall Street Journal, citing Datamonitor, reported that people are going to seek more mindfulness and meditation apps. I expect more people will turn to voice interfaces to find wellness information and mindfulness tools. Managing mental health. reported as part of a broader contact-free experience: ordering and having products delivered end to end, completely no touch. Shopping as people living in lockdown have more time on their hands. Unfortunately, layoffs and job furloughs are also on the rise, and people living at home are going to use this time for self-improvement. Learning On the other hand, voice usage in the car will decrease (and presumably already has) even as people gradually start leaving their homes in limited numbers with states easing shelter-in-place mandates. People are not driving as much, and therefore they simply don’t need to use voice assistants for way-finding and other uses. (But randomized walking paths might become more common because they allow for routing of foot traffic through non-crowded locales.) Another area to watch: on the job. Technically, using voice to manage in-office tasks such as booking a conference room will continue to plummet. But with “on the job” now meaning working at home, it will be interesting to see how people use voice to manage remote working beyond video conferencing perhaps utilizing dictation for note-taking and action items. Now is the time for businesses to watch changing consumer behavior closely. The time to invest in voice is now. Don’t wait until “we get through this.” The dawn of a new day is on the horizon.

VOICEITT

voiceitt.com

-- employees

Since n.d.

COMPANY RANKING

VOICEITT

EVERGREEN INDEX #11166

Representing this company? Click here to claim and customize this page!

Voiceitt WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

VOICEITT

voiceitt.com

-- employees

Since n.d.

COMPANY RANKING

VOICEITT

EVERGREEN INDEX #11166

RELATED COMPANIESRANK

STORIES ABOUT VOICEITT

Representing this company? Click here to claim and customize this page!

Voiceitt WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!