Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework

no code implementations • 27 Jun 2022 • Rahil Parikh, Harshavardhan Sundar, Ming Sun, Chao Wang, Spyros Matsoukas

We conclude that this improvement in ASC performance comes from the regularization effect of using AET and not from the network's improved ability to discern between acoustic events.

Acoustic Scene Classification Multi-Task Learning +1

Who Spoke What? A Latent Variable Framework for the Joint Decoding of Multiple Speakers and their Keywords

no code implementations • 29 Apr 2015 • Harshavardhan Sundar, Thippur V. Sreenivas

The distribution of the mixture signal is expressed in terms of the LV mass functions and speaker-specific-keyword models.