Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling

Fang Zheng; Zhanjiang Song; Pascale Fung; William Byrne

Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling

Fang Zheng, Zhanjiang Song, Pascale Fung, William Byrne

Department of Electronic and Computer Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

4 Citations (Scopus)

Abstract

The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF) characteristics of Chinese language and developing the Bayesian equation, we propose the concepts of generalized initial/final (GIF) and generalized syllable (GS), the GIF modeling method and the IF-GIF modeling method, as well as the context-dependent pronunciation weighting method. By using these approaches, the IF-GIF modeling reduces the Chinese syllable error rate (SER) by 6.3% and 4.2% compared with the GIF modeling and IF modeling respectively when the language modeling, such as syllable or word N-gram, is not used.

Original language	English
Title of host publication	EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
Editors	Borge Lindberg, Henrik Benner, Paul Dalsgaard, Zheng-Hua Tan
Publisher	International Speech Communication Association
Pages	57-60
Number of pages	4
ISBN (Electronic)	8790834100, 9788790834104
Publication status	Published - 2001
Event	7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark Duration: 3 Sept 2001 → 7 Sept 2001

Publication series

Name	EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Conference

Conference	7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
Country/Territory	Denmark
City	Aalborg
Period	3/09/01 → 7/09/01

Cite this

Zheng, F., Song, Z., Fung, P., & Byrne, W. (2001). Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling. In B. Lindberg, H. Benner, P. Dalsgaard, & Z.-H. Tan (Eds.), EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (pp. 57-60). (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology). International Speech Communication Association.

Zheng, Fang ; Song, Zhanjiang ; Fung, Pascale et al. / Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. editor / Borge Lindberg ; Henrik Benner ; Paul Dalsgaard ; Zheng-Hua Tan. International Speech Communication Association, 2001. pp. 57-60 (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

@inproceedings{30bc465c96c146f8a662c690d38d8a34,

title = "Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling",

abstract = "The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF) characteristics of Chinese language and developing the Bayesian equation, we propose the concepts of generalized initial/final (GIF) and generalized syllable (GS), the GIF modeling method and the IF-GIF modeling method, as well as the context-dependent pronunciation weighting method. By using these approaches, the IF-GIF modeling reduces the Chinese syllable error rate (SER) by 6.3\% and 4.2\% compared with the GIF modeling and IF modeling respectively when the language modeling, such as syllable or word N-gram, is not used.",

author = "Fang Zheng and Zhanjiang Song and Pascale Fung and William Byrne",

year = "2001",

language = "English",

series = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",

publisher = "International Speech Communication Association",

pages = "57--60",

editor = "Borge Lindberg and Henrik Benner and Paul Dalsgaard and Zheng-Hua Tan",

booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",

note = "7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 ; Conference date: 03-09-2001 Through 07-09-2001",

}

Zheng, F, Song, Z, Fung, P & Byrne, W 2001, Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling. in B Lindberg, H Benner, P Dalsgaard & Z-H Tan (eds), EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology, International Speech Communication Association, pp. 57-60, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Denmark, 3/09/01.

Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling. / Zheng, Fang; Song, Zhanjiang; Fung, Pascale et al.
EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. ed. / Borge Lindberg; Henrik Benner; Paul Dalsgaard; Zheng-Hua Tan. International Speech Communication Association, 2001. p. 57-60 (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling

AU - Zheng, Fang

AU - Song, Zhanjiang

AU - Fung, Pascale

AU - Byrne, William

PY - 2001

Y1 - 2001

N2 - The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF) characteristics of Chinese language and developing the Bayesian equation, we propose the concepts of generalized initial/final (GIF) and generalized syllable (GS), the GIF modeling method and the IF-GIF modeling method, as well as the context-dependent pronunciation weighting method. By using these approaches, the IF-GIF modeling reduces the Chinese syllable error rate (SER) by 6.3% and 4.2% compared with the GIF modeling and IF modeling respectively when the language modeling, such as syllable or word N-gram, is not used.

AB - The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF) characteristics of Chinese language and developing the Bayesian equation, we propose the concepts of generalized initial/final (GIF) and generalized syllable (GS), the GIF modeling method and the IF-GIF modeling method, as well as the context-dependent pronunciation weighting method. By using these approaches, the IF-GIF modeling reduces the Chinese syllable error rate (SER) by 6.3% and 4.2% compared with the GIF modeling and IF modeling respectively when the language modeling, such as syllable or word N-gram, is not used.

UR - https://www.scopus.com/pages/publications/85009089398

M3 - Conference Paper published in a book

AN - SCOPUS:85009089398

T3 - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

SP - 57

EP - 60

BT - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

A2 - Lindberg, Borge

A2 - Benner, Henrik

A2 - Dalsgaard, Paul

A2 - Tan, Zheng-Hua

PB - International Speech Communication Association

T2 - 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001

Y2 - 3 September 2001 through 7 September 2001

ER -

Zheng F, Song Z, Fung P, Byrne W. Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling. In Lindberg B, Benner H, Dalsgaard P, Tan ZH, editors, EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 57-60. (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this