Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches

Chien Lin Huang; Chung Hsien Wu; Haizhou Li; Chia Hsin Hsieh; Bin Ma

doi:10.1109/ICME.2008.4607630

Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches

Chien Lin Huang, Chung Hsien Wu, Haizhou Li, Chia Hsin Hsieh, Bin Ma

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This study presents a novel approach to unsupervised pronunciation grammar growing for non-native speech recognition. Unsupervised pronunciation grammar growing includes pronunciation variation graph construction and non-native grammar generation. Knowledge-based and data-driven approaches are considered for variation graph construction. The measurement of confidence and support is used for grammar selection. Experiments show that unsupervised pronunciation grammar growing is suitable for the improvement of non-native speech recognition.

Original language	English
Title of host publication	2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings
Pages	1097-1100
Number of pages	4
DOIs	https://doi.org/10.1109/ICME.2008.4607630
Publication status	Published - 2008
Event	2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Hannover, Germany Duration: 2008 Jun 23 → 2008 Jun 26

Publication series

Name	2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings

Other

Other	2008 IEEE International Conference on Multimedia and Expo, ICME 2008
Country/Territory	Germany
City	Hannover
Period	08-06-23 → 08-06-26

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering

Access to Document

10.1109/ICME.2008.4607630

Cite this

Huang, C. L., Wu, C. H., Li, H., Hsieh, C. H., & Ma, B. (2008). Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches. In 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings (pp. 1097-1100). Article 4607630 (2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings). https://doi.org/10.1109/ICME.2008.4607630

@inproceedings{f781383d0b9b491f95ab98d3792ec53c,

title = "Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches",

abstract = "This study presents a novel approach to unsupervised pronunciation grammar growing for non-native speech recognition. Unsupervised pronunciation grammar growing includes pronunciation variation graph construction and non-native grammar generation. Knowledge-based and data-driven approaches are considered for variation graph construction. The measurement of confidence and support is used for grammar selection. Experiments show that unsupervised pronunciation grammar growing is suitable for the improvement of non-native speech recognition.",

author = "Huang, {Chien Lin} and Wu, {Chung Hsien} and Haizhou Li and Hsieh, {Chia Hsin} and Bin Ma",

note = "Funding Information: This work was supported in part by Research Grant from NPIU under “TEQIP-III Collaborative Research Scheme” ( 1-5748247251 ). The authors are grateful to Department of Ceramic Engineering IIT (BHU) for providing the measurement facility.; 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 ; Conference date: 23-06-2008 Through 26-06-2008",

year = "2008",

doi = "10.1109/ICME.2008.4607630",

language = "English",

isbn = "9781424425716",

series = "2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings",

pages = "1097--1100",

booktitle = "2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings",

}

Huang, CL, Wu, CH, Li, H, Hsieh, CH & Ma, B 2008, Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches. in 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings., 4607630, 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings, pp. 1097-1100, 2008 IEEE International Conference on Multimedia and Expo, ICME 2008, Hannover, Germany, 08-06-23. https://doi.org/10.1109/ICME.2008.4607630

Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches. / Huang, Chien Lin; Wu, Chung Hsien; Li, Haizhou et al.
2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings. 2008. p. 1097-1100 4607630 (2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches

AU - Huang, Chien Lin

AU - Wu, Chung Hsien

AU - Li, Haizhou

AU - Hsieh, Chia Hsin

AU - Ma, Bin

N1 - Funding Information: This work was supported in part by Research Grant from NPIU under “TEQIP-III Collaborative Research Scheme” ( 1-5748247251 ). The authors are grateful to Department of Ceramic Engineering IIT (BHU) for providing the measurement facility.

PY - 2008

Y1 - 2008

N2 - This study presents a novel approach to unsupervised pronunciation grammar growing for non-native speech recognition. Unsupervised pronunciation grammar growing includes pronunciation variation graph construction and non-native grammar generation. Knowledge-based and data-driven approaches are considered for variation graph construction. The measurement of confidence and support is used for grammar selection. Experiments show that unsupervised pronunciation grammar growing is suitable for the improvement of non-native speech recognition.

AB - This study presents a novel approach to unsupervised pronunciation grammar growing for non-native speech recognition. Unsupervised pronunciation grammar growing includes pronunciation variation graph construction and non-native grammar generation. Knowledge-based and data-driven approaches are considered for variation graph construction. The measurement of confidence and support is used for grammar selection. Experiments show that unsupervised pronunciation grammar growing is suitable for the improvement of non-native speech recognition.

UR - http://www.scopus.com/inward/record.url?scp=54049105804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54049105804&partnerID=8YFLogxK

U2 - 10.1109/ICME.2008.4607630

DO - 10.1109/ICME.2008.4607630

M3 - Conference contribution

AN - SCOPUS:54049105804

SN - 9781424425716

T3 - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings

SP - 1097

EP - 1100

BT - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings

T2 - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008

Y2 - 23 June 2008 through 26 June 2008

ER -

Unsupervised pronunciation grammar growing using knowledge-based and data-driven approaches

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this