Investigation of DNN-based audio-visual speech recognition

Satoshi Tamura, Hiroshi Ninomiya, Norihide Kitaoka, Shin Osuga, Yurie Iribe, Kazuya Takeda, Satoru Hayamizu

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Audio-Visual Speech Recognition (AVSR) is one of techniques to enhance robustness of speech recognizer in noisy or real environments. On the other hand, Deep Neural Networks (DNNs) have recently attracted a lot of attentions of researchers in the speech recognition field, because we can drastically improve recognition performance by using DNNs. There are two ways to employ DNN techniques for speech recognition: a hybrid approach and a tandem approach; in the hybrid approach an emission probability on each Hidden Markov Model (HMM) state is computed using a DNN, while in the tandem approach a DNN is composed into a feature extraction scheme. In this paper, we investigate and compare several DNN-based AVSR methods to mainly clarify how we should incorporate audio and visual modalities using DNNs. We carried out recognition experiments using a corpus CENSREC-1-AV, and we discuss the results to find out the best DNN-based AVSR modeling. Then it turns out that a tandembased method using audio Deep Bottle-Neck Features (DBNFs) and visual ones with multi-stream HMMs is the most suitable, followed by a hybrid approach and another tandem scheme using audio-visual DBNFs.

Original languageEnglish
Pages (from-to)2444-2451
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE99D
Issue number10
DOIs
Publication statusPublished - 2016 Oct
Externally publishedYes

Keywords

  • Audio-visual speech recognition
  • Deep Bottleneck Feature
  • Deep neural network
  • Multi-stream HMM

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Investigation of DNN-based audio-visual speech recognition'. Together they form a unique fingerprint.

Cite this