Learning Sound Events From Webly Labeled Data

In this work, we introduce webly labeled learning for sound events in which we aim to remove human supervision altogether from the learning process . We first develop a method of obtaining labeled audio data from the web (albeit noisy) in which no manual labeling is involved . In our proposed system, WeblyNet, two deep neural networks co-teach each other to robustly learn from Webly labeled data, leading to around 17% relative improvement over the baseline method . The method also involves transfer learning to obtain efficient representations . The proposed system is Webly net, which is based on a proposed system from the company .

Links: PDF - Abstract

Code :

https://github.com/anuragkr90/webly-labeled-sounds

Keywords : webly - labeled - learning - system - data -

Leave a Reply

Your email address will not be published. Required fields are marked *