Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform

D. Kim, Dongsuk Yook

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

A transform-based adaptation algorithm for robust speech recognition in unknown environments is proposed. In the cepstral domain, it is difficult to handle environmental noise. The proposed approach deals with such noise in the linear spectral domain, so that a small number of parameters can be used for fast adaptation.

Original languageEnglish
Pages (from-to)632-634
Number of pages3
JournalElectronics Letters
Volume40
Issue number10
DOIs
Publication statusPublished - 2004 May 13

Fingerprint

Speech recognition
Maximum likelihood
Mathematical transformations

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform. / Kim, D.; Yook, Dongsuk.

In: Electronics Letters, Vol. 40, No. 10, 13.05.2004, p. 632-634.

Research output: Contribution to journalArticle

@article{304531114e814992832eb80e5feb36a0,
title = "Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform",
abstract = "A transform-based adaptation algorithm for robust speech recognition in unknown environments is proposed. In the cepstral domain, it is difficult to handle environmental noise. The proposed approach deals with such noise in the linear spectral domain, so that a small number of parameters can be used for fast adaptation.",
author = "D. Kim and Dongsuk Yook",
year = "2004",
month = "5",
day = "13",
doi = "10.1049/el:20040395",
language = "English",
volume = "40",
pages = "632--634",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "10",

}

TY - JOUR

T1 - Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform

AU - Kim, D.

AU - Yook, Dongsuk

PY - 2004/5/13

Y1 - 2004/5/13

N2 - A transform-based adaptation algorithm for robust speech recognition in unknown environments is proposed. In the cepstral domain, it is difficult to handle environmental noise. The proposed approach deals with such noise in the linear spectral domain, so that a small number of parameters can be used for fast adaptation.

AB - A transform-based adaptation algorithm for robust speech recognition in unknown environments is proposed. In the cepstral domain, it is difficult to handle environmental noise. The proposed approach deals with such noise in the linear spectral domain, so that a small number of parameters can be used for fast adaptation.

UR - http://www.scopus.com/inward/record.url?scp=2942620285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942620285&partnerID=8YFLogxK

U2 - 10.1049/el:20040395

DO - 10.1049/el:20040395

M3 - Article

AN - SCOPUS:2942620285

VL - 40

SP - 632

EP - 634

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 10

ER -