CNN-based multichannel end-to-end speech recognition for everyday home environments

Nelson Yalta, Shinji Watanabe, Takaaki Hori, Kazuhiro Nakadai, Tetsuya Ogata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of environments are the target of the CHiME-5 challenge. By employing a convolutional neural network (CNN)-based multichannel end-to-end speech recognition system, this study attempts to overcome the presents difficulties in everyday environments. The system comprises of an attention-based encoder-decoder neural network that directly generates a text as an output from a sound input. The multichannel CNN encoder, which uses residual connections and batch renormalization, is trained with augmented data, including white noise injection. The experimental results show that the word error rate is reduced by 8.5% and 0.6% absolute from a single channel end-to-end and the best baseline (LF-MMI TDNN) on the CHiME-5 corpus, respectively.

Original languageEnglish
Title of host publicationEUSIPCO 2019 - 27th European Signal Processing Conference
PublisherEuropean Signal Processing Conference, EUSIPCO
ISBN (Electronic)9789082797039
DOIs
Publication statusPublished - 2019 Sep
Event27th European Signal Processing Conference, EUSIPCO 2019 - A Coruna, Spain
Duration: 2019 Sep 22019 Sep 6

Publication series

NameEuropean Signal Processing Conference
Volume2019-September
ISSN (Print)2219-5491

Conference

Conference27th European Signal Processing Conference, EUSIPCO 2019
CountrySpain
CityA Coruna
Period19/9/219/9/6

Keywords

  • End-to-end speech recognition
  • Multichannel
  • Residual networks

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'CNN-based multichannel end-to-end speech recognition for everyday home environments'. Together they form a unique fingerprint.

Cite this