On-line adaptation and Bayesian detection of environmental changes based on a macroscopic time evolution system

Shinji Watanabe, Atsushi Nakamura

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

3 Citations (Scopus)

Abstract

Acoustic characteristics are often changed over time as a result of various factors including changes of speakers, speaking styles, and noise sources. Incremental adaptation techniques for speech recognition are aimed at adjusting acoustic models quickly and stably to such time-variant acoustic characteristics. Recently we proposed a novel incremental adaptation framework based on a macroscopic time evolution system, which models the time-variant characteristics by successively updating posterior distributions of acoustic model parameters. This paper proposes fast incremental adaptation based on a macroscopic time evolution system that realizes an utterance-by-utterance update by approximating the posterior distributions. This adaptation was used to perform on-line adaptation of Japanese broadcast news for very large vocabulary continuous speech recognition (700k vocabulary size) in real time. The word accuracy was improved from 73.9% to 85.1%. In addition, by incorporating a Bayesian model selection approach, we realized the simultaneous on-line adaptation and detection of environmental changes.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009
Pages4373-4376
Number of pages4
DOIs
Publication statusPublished - 2009 Sep 23
Externally publishedYes
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China
Duration: 2009 Apr 192009 Apr 24

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
CountryTaiwan, Province of China
CityTaipei
Period09/4/1909/4/24

Keywords

  • Acoustic model
  • Macroscopic time evolution system
  • Model selection
  • On-line adaptation
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'On-line adaptation and Bayesian detection of environmental changes based on a macroscopic time evolution system'. Together they form a unique fingerprint.

  • Cite this

    Watanabe, S., & Nakamura, A. (2009). On-line adaptation and Bayesian detection of environmental changes based on a macroscopic time evolution system. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009 (pp. 4373-4376). [4960598] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2009.4960598