Robust Speech Recognition Using Generative Adversarial Networks

Anuroop Sriram; Heewoo Jun; Yashesh Gaur; Sanjeev Satheesh

ICASSP 2018accepted0 citations

Robust Speech Recognition Using Generative Adversarial Networks

Anuroop Sriram, Heewoo Jun, Yashesh Gaur, Sanjeev Satheesh

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 does not rely on domain expertise or strong assumptions, and directly encourages robustness in a data-driven way. We show the new approach improves simulated far-field speech recognition of vanilla sequence-to-sequence models without specialized front-ends or preprocessing.

BibTeX

@inproceedings{icassp2018_robustspeechreco,
  title = {Robust Speech Recognition Using Generative Adversarial Networks},
  author = {Anuroop Sriram and Heewoo Jun and Yashesh Gaur and Sanjeev Satheesh},
  booktitle = {ICASSP 2018},
  year = {2018}
}