Predictor—Corrector Adaptation by Using Time Evolution System With Macroscopic Time Scale

Shinji Watanabe, Atsushi Nakamura

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


Incremental adaptation techniques for speech recognition are aimed at adjusting acoustic models to time-variant acoustic characteristics related to such factors as changes of speaker, speaking style, and noise source over time. In this paper, we propose a novel incremental adaptation framework, which models such time-variant characteristics by successively updating posterior distributions of acoustic model parameters based on a macroscopic time scale (e.g., every set of more than a dozen utterances). The proposed incremental update involves a predictor-corrector algorithm based on a macroscopic time evolution system in accordance with the Kalman filter theory. We also 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 realizes the predictor-corrector algorithm and involves both the conventional and their combinatorial adaptation approaches. Consequently, the proposal achieves robust recognition performance based on a balanced incremental adaptation between quickness and stability.

Original languageEnglish
Pages (from-to)395-406
Number of pages12
JournalIEEE Transactions on Audio, Speech and Language Processing
Issue number2
Publication statusPublished - 2010 Feb
Externally publishedYes


  • Acoustic model
  • incremental adaptation
  • macroscopic time evolution
  • predictor-corrector algorithm
  • speech recognition

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Predictor—Corrector Adaptation by Using Time Evolution System With Macroscopic Time Scale'. Together they form a unique fingerprint.

Cite this