DeepAI AI Chat
Log In Sign Up

Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling

by   Peidong Wang, et al.
The Ohio State University

Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition. Experimental results suggest that distortion-independent acoustic modeling is able to overcome the distortion problem. Such an acoustic model can also work with speech enhancement models different from the one used during training. Moreover, the models investigated in this paper outperform the previous best system on the CHiME-2 corpus.


Time-Domain Speech Enhancement for Robust Automatic Speech Recognition

It has been shown that the intelligibility of noisy speech can be improv...

Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions

The deep learning based time-domain models, e.g. Conv-TasNet, have shown...

Perceptual Loss with Recognition Model for Single-Channel Enhancement and Robust ASR

Single-channel speech enhancement approaches do not always improve autom...

Effect of noise suppression losses on speech distortion and ASR performance

Deep learning based speech enhancement has made rapid development toward...

Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition

The joint training framework for speech enhancement and recognition meth...

Dual Application of Speech Enhancement for Automatic Speech Recognition

In this work, we exploit speech enhancement for improving a recurrent ne...

A network of deep neural networks for distant speech recognition

Despite the remarkable progress recently made in distant speech recognit...