Stream Attention for far-field multi-microphone ASR

A stream attention framework has been applied to the posterior probabilities of the deep neural network (DNN) to improve the far-field automatic speech recognition (ASR) performance in the multi-microphone configuration. The stream attention scheme has been realized through an attention vector, whic...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wang, Xiaofei, Yan, Yonghong, Hermansky, Hynek
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 29.11.2017
Subjects
Automatic speech recognition
Microphones
Neural networks
Performance prediction
Online AccessGet full text

Cover

More Information
Summary:A stream attention framework has been applied to the posterior probabilities of the deep neural network (DNN) to improve the far-field automatic speech recognition (ASR) performance in the multi-microphone configuration. The stream attention scheme has been realized through an attention vector, which is derived by predicting the ASR performance from the phoneme posterior distribution of individual microphone stream, focusing the recognizer's attention to more reliable microphones. Investigation on the various ASR performance measures has been carried out using the real recorded dataset. Experiments results show that the proposed framework has yielded substantial improvements in word error rate (WER).
ISSN:2331-8422