Jyotika Singh

I am a Data Scientist living in San Diego and a UCLA Master's graduate. I'm passionate about solving problems using the power of Data and Machine Learning.

Audio processing and ML using python

ML, AI, & Data, Python & Libraries, Intermediate
8/17/2019 | 3:45 PM-4:10 PM | Boardroom


Challenges with Audio Classification problems focussing on cleaning and building features from audio which can then be used to build a classification model, features that work well with audio and speech data and the open source libraries useful for the same.


Audio data, unlike other data, needs a bit of a different approach while trying to extract information and building classification models. I will talk about cleaning audio signal approaches, how to form features from an audio and what features help extract the unseen information that can help with classification models.