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

D. Kim; D. Yook

doi:10.1049/el:20040395

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

D. Kim, D. Yook

Research output: Contribution to journal › Article › peer-review

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 language	English
Pages (from-to)	632-634
Number of pages	3
Journal	Electronics Letters
Volume	40
Issue number	10
DOIs	https://doi.org/10.1049/el:20040395
Publication status	Published - 2004 May 13

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1049/el:20040395

Cite this

@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 D. Yook",

year = "2004",

month = may,

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, D.

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

U2 - 10.1049/el:20040395

DO - 10.1049/el:20040395

M3 - Article

AN - SCOPUS:2942620285

SN - 0013-5194

VL - 40

SP - 632

EP - 634

JO - Electronics Letters

JF - Electronics Letters

IS - 10

ER -

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

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this