Incremental adaptation based on a macroscopic time evolution system

Shinji Watanabe, Atsushi Nakamura

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

3 Citations (Scopus)

Abstract

In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Volume4
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI
Duration: 2007 Apr 152007 Apr 20

Other

Other2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
CityHonolulu, HI
Period07/4/1507/4/20

Fingerprint

Random processes
Kalman filters
stochastic processes
propagation

Keywords

  • Acoustic model
  • Discrete stochastic process
  • Incremental adaptation
  • Macroscopic time evolution
  • Speech recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Watanabe, S., & Nakamura, A. (2007). Incremental adaptation based on a macroscopic time evolution system. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 (Vol. 4). [4218214] https://doi.org/10.1109/ICASSP.2007.367026

Incremental adaptation based on a macroscopic time evolution system. / Watanabe, Shinji; Nakamura, Atsushi.

2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. Vol. 4 2007. 4218214.

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

Watanabe, S & Nakamura, A 2007, Incremental adaptation based on a macroscopic time evolution system. in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. vol. 4, 4218214, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, Honolulu, HI, 07/4/15. https://doi.org/10.1109/ICASSP.2007.367026
Watanabe S, Nakamura A. Incremental adaptation based on a macroscopic time evolution system. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. Vol. 4. 2007. 4218214 https://doi.org/10.1109/ICASSP.2007.367026
Watanabe, Shinji ; Nakamura, Atsushi. / Incremental adaptation based on a macroscopic time evolution system. 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. Vol. 4 2007.
@inproceedings{a00885e55be84ba7b5237c950d924cab,
title = "Incremental adaptation based on a macroscopic time evolution system",
abstract = "In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.",
keywords = "Acoustic model, Discrete stochastic process, Incremental adaptation, Macroscopic time evolution, Speech recognition",
author = "Shinji Watanabe and Atsushi Nakamura",
year = "2007",
doi = "10.1109/ICASSP.2007.367026",
language = "English",
isbn = "1424407281",
volume = "4",
booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",

}

TY - GEN

T1 - Incremental adaptation based on a macroscopic time evolution system

AU - Watanabe, Shinji

AU - Nakamura, Atsushi

PY - 2007

Y1 - 2007

N2 - In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.

AB - In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.

KW - Acoustic model

KW - Discrete stochastic process

KW - Incremental adaptation

KW - Macroscopic time evolution

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=34547552788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547552788&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2007.367026

DO - 10.1109/ICASSP.2007.367026

M3 - Conference contribution

SN - 1424407281

SN - 9781424407286

VL - 4

BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

ER -