Speaker adaptation for Hidden Marcov models

D. Shaked; A. Cohen

doi:10.1109/EEIS.1989.720122

Speaker adaptation for Hidden Marcov models

D. Shaked, A. Cohen

Department of Electrical & Computer Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper proposes an algorithm for adaptive training of a Hidden Markov Model (HMM) in an Automatic Speech Recognition (ASR) System. The adaptive training procedure uses the Viterbi algorithm. A forgeting factor enables regulation of the model's adaptation dynamics as well as the steady state stability, according to a planed adaptation policy. The proposed algorithm was tested by synthesized data, generated by HMMs similar to models used for in speech recognition. Results of the simulation using the divergence measure, illustrate the effect of various adaptation policies, on the adaptation time and accuracy.

Original language	English
DOIs	https://doi.org/10.1109/EEIS.1989.720122
State	Published - 1 Jan 1989
Event	16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989 - Tel-Aviv, Israel Duration: 7 Mar 1989 → 9 Mar 1989

Conference

Conference	16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989
Country/Territory	Israel
City	Tel-Aviv
Period	7/03/89 → 9/03/89

ASJC Scopus subject areas

Software
Computer Networks and Communications
Signal Processing
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/EEIS.1989.720122

Cite this

@conference{291a14e35a2b4b12942f75b7346fe97a,

title = "Speaker adaptation for Hidden Marcov models",

abstract = "This paper proposes an algorithm for adaptive training of a Hidden Markov Model (HMM) in an Automatic Speech Recognition (ASR) System. The adaptive training procedure uses the Viterbi algorithm. A forgeting factor enables regulation of the model's adaptation dynamics as well as the steady state stability, according to a planed adaptation policy. The proposed algorithm was tested by synthesized data, generated by HMMs similar to models used for in speech recognition. Results of the simulation using the divergence measure, illustrate the effect of various adaptation policies, on the adaptation time and accuracy.",

author = "D. Shaked and A. Cohen",

note = "Publisher Copyright: {\textcopyright} 1990 IEEE.; 16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989 ; Conference date: 07-03-1989 Through 09-03-1989",

year = "1989",

month = jan,

day = "1",

doi = "10.1109/EEIS.1989.720122",

language = "English",

}

TY - CONF

T1 - Speaker adaptation for Hidden Marcov models

AU - Shaked, D.

AU - Cohen, A.

PY - 1989/1/1

Y1 - 1989/1/1

N2 - This paper proposes an algorithm for adaptive training of a Hidden Markov Model (HMM) in an Automatic Speech Recognition (ASR) System. The adaptive training procedure uses the Viterbi algorithm. A forgeting factor enables regulation of the model's adaptation dynamics as well as the steady state stability, according to a planed adaptation policy. The proposed algorithm was tested by synthesized data, generated by HMMs similar to models used for in speech recognition. Results of the simulation using the divergence measure, illustrate the effect of various adaptation policies, on the adaptation time and accuracy.

AB - This paper proposes an algorithm for adaptive training of a Hidden Markov Model (HMM) in an Automatic Speech Recognition (ASR) System. The adaptive training procedure uses the Viterbi algorithm. A forgeting factor enables regulation of the model's adaptation dynamics as well as the steady state stability, according to a planed adaptation policy. The proposed algorithm was tested by synthesized data, generated by HMMs similar to models used for in speech recognition. Results of the simulation using the divergence measure, illustrate the effect of various adaptation policies, on the adaptation time and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85067359022&partnerID=8YFLogxK

U2 - 10.1109/EEIS.1989.720122

DO - 10.1109/EEIS.1989.720122

M3 - Paper

AN - SCOPUS:85067359022

T2 - 16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989

Y2 - 7 March 1989 through 9 March 1989

ER -

Speaker adaptation for Hidden Marcov models

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this