Intro to Audio Analysis: Recognizing Sounds Using Machine Learning

Written by tyiannak | Published 2020/09/12
Tech Story Tags: machinelearning | machine-learning-tutorials | python | ai | speech-recognition | artificial-intelligence | audio-content | data-science | hackernoon-es

TLDR Sound analysis is a challenging task associated to various modern applications, such as speech analytics, music information retrieval, speaker recognition, behavioral analytics and auditory scene analysis for security, health and environmental monitoring. This article provides a brief introduction to basic concepts of audio feature extraction, sound classification and sound classification. Python examples are provided in all cases, mostly through the pyAudioAnalysis library. All examples are also provided in this GitHub repo. In this article, this article focuses on hand-crafted audio features and traditional statistical classifiers.via the TL;DR App

no story

Written by tyiannak | I make algorithms that understand sounds
Published by HackerNoon on 2020/09/12