A unified interpretation of adaptation approaches based on a macroscopic time evolution system and indirect/direct adaptation approaches

Shinji Watanabe, Atsushi Nakamura

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

3 Citations (Scopus)

Abstract

Incremental adaptation techniques for speech recognition are aimed at adjusting acoustic models quickly and stably to time-variant acoustic characteristics due to temporal changes of speaker, speaking style, noise source, etc. 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. In this paper, we provide a unified interpretation of the proposal and the two major conventional approaches of indirect adaptation via transformation parameters (e.g. Maximum Likelihood Linear Regression (MLLR)) and direct adaptation of classifier parameters (e.g. Maximum A Posteriori (MAP)). We reveal analytically and experimentally that the proposed incremental adaptation involves both the conventional and their combinatorial approaches, and simultaneously possesses their quick and stable adaptation characteristics.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages4285-4288
Number of pages4
DOIs
Publication statusPublished - 2008 Sep 16
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: 2008 Mar 312008 Apr 4

Publication series

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

Conference

Conference2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period08/3/3108/4/4

Keywords

  • Acoustic model
  • Incremental adaptation
  • Indirect/direct adaptation
  • Macroscopic time evolution
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A unified interpretation of adaptation approaches based on a macroscopic time evolution system and indirect/direct adaptation approaches'. Together they form a unique fingerprint.

  • Cite this

    Watanabe, S., & Nakamura, A. (2008). A unified interpretation of adaptation approaches based on a macroscopic time evolution system and indirect/direct adaptation approaches. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 4285-4288). [4518602] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4518602