Speaker adaptation based on MAP estimation using fuzzy controller

Yau Tarng Juang; Kuo Chang Huang; Ing Jr Ding

doi:10.1016/S0167-8655(03)00125-9

Speaker adaptation based on MAP estimation using fuzzy controller

Yau Tarng Juang, Kuo Chang Huang, Ing Jr Ding

Department of Electrical Engineering

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

7 Scopus citations

Abstract

This paper presents a technical speaker adaptation method called FCMAP, which incorporated an appropriate fuzzy logic controller into maximum a posteriori (MAP) to adapt the hidden Markov model parameters. Experimental results show that the speaker adaptation system using the FCMAP adaptation method outperforms that of the conventional MAP, especially when only few utterances from a new speaker are available for adaptation.

Original language	English
Pages (from-to)	2807-2813
Number of pages	7
Journal	Pattern Recognition Letters
Volume	24
Issue number	15
DOIs	https://doi.org/10.1016/S0167-8655(03)00125-9
State	Published - Nov 2003

Keywords

Fuzzy logic
Hidden Markov model adaptation
Maximum a posteriori adaptation
Speaker adaptation

Access to Document

10.1016/S0167-8655(03)00125-9

Cite this

@article{371eb5d195bd4860965f3c93a1efb46c,

title = "Speaker adaptation based on MAP estimation using fuzzy controller",

abstract = "This paper presents a technical speaker adaptation method called FCMAP, which incorporated an appropriate fuzzy logic controller into maximum a posteriori (MAP) to adapt the hidden Markov model parameters. Experimental results show that the speaker adaptation system using the FCMAP adaptation method outperforms that of the conventional MAP, especially when only few utterances from a new speaker are available for adaptation.",

keywords = "Fuzzy logic, Hidden Markov model adaptation, Maximum a posteriori adaptation, Speaker adaptation",

author = "Juang, {Yau Tarng} and Huang, {Kuo Chang} and Ding, {Ing Jr}",

note = "Funding Information: The work was partially supported by the National Science Council of the Republic of China under the contract NSC89-2218-E-008-004. ",

year = "2003",

month = nov,

doi = "10.1016/S0167-8655(03)00125-9",

language = "???core.languages.en_GB???",

volume = "24",

pages = "2807--2813",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

number = "15",

}

TY - JOUR

T1 - Speaker adaptation based on MAP estimation using fuzzy controller

AU - Juang, Yau Tarng

AU - Huang, Kuo Chang

AU - Ding, Ing Jr

N1 - Funding Information: The work was partially supported by the National Science Council of the Republic of China under the contract NSC89-2218-E-008-004.

PY - 2003/11

Y1 - 2003/11

N2 - This paper presents a technical speaker adaptation method called FCMAP, which incorporated an appropriate fuzzy logic controller into maximum a posteriori (MAP) to adapt the hidden Markov model parameters. Experimental results show that the speaker adaptation system using the FCMAP adaptation method outperforms that of the conventional MAP, especially when only few utterances from a new speaker are available for adaptation.

AB - This paper presents a technical speaker adaptation method called FCMAP, which incorporated an appropriate fuzzy logic controller into maximum a posteriori (MAP) to adapt the hidden Markov model parameters. Experimental results show that the speaker adaptation system using the FCMAP adaptation method outperforms that of the conventional MAP, especially when only few utterances from a new speaker are available for adaptation.

KW - Fuzzy logic

KW - Hidden Markov model adaptation

KW - Maximum a posteriori adaptation

KW - Speaker adaptation

UR - http://www.scopus.com/inward/record.url?scp=0042830826&partnerID=8YFLogxK

U2 - 10.1016/S0167-8655(03)00125-9

DO - 10.1016/S0167-8655(03)00125-9

M3 - 期刊論文

AN - SCOPUS:0042830826

SN - 0167-8655

VL - 24

SP - 2807

EP - 2813

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 15

ER -

Speaker adaptation based on MAP estimation using fuzzy controller

Abstract

Keywords

Access to Document

Fingerprint

Cite this