Learning Sound Events From Webly Labeled Data
This work addresses the need for automated audio event detection by reducing reliance on manual labeling, though it is incremental in building on weakly labeled learning approaches.
The paper tackles the problem of learning sound events without human supervision by using webly labeled data, achieving a 17% relative improvement over baseline methods with their WeblyNet system.
In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims 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. We then describe methods to efficiently learn from these webly labeled audio recordings. 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