Robust Speech Recognition Using Generative Adversarial Networks

Abstract

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by learning to map noisy audio to the same embedding space as that of clean audio. Unlike previous methods, the new framework… (More)

4 Figures and Tables

Topics

  • Presentations referencing similar topics