Code-Switching Speech Detection Method by Combination of Language and Acoustic Information

Hong Ji Zhang

doi:10.4028/www.scientific.net/AMR.756-759.3622

Paper Titles

Coarse Frequency Offset Estimation of TD-LTE Based on Spectrum Centroid
p.3602

Transient Signal Feature Extraction Based on Box Dimension and the Largest Lyapunov Dimension
p.3607

Control Algorithm Optimization of Electric Air Conditioning Based on ADVISOR
p.3611

A Cross-Entropy Method for Solving Passenger Flow Routing Problem
p.3617

Code-Switching Speech Detection Method by Combination of Language and Acoustic Information
p.3622

The Strong Convergence of a New Iterative Algorithm for Asymptotically Nonexpansive Mappings
p.3628

Algebraic Techniques in Linear Cryptanalysis
p.3634

An Evaluation Method of Combat Service Operation Performance for Surface-to-Air Missile Based on FNN
p.3640

A New Hybrid GRASP with the Pilot Method Forthe Delay-Constrained Multicast Routing Problem
p.3647

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 756-759Code-Switching Speech Detection Method by...

Code-Switching Speech Detection Method by Combination of Language and Acoustic Information

Abstract:

In this paper, we propose a new speech detection method to English-Mandarin code-switching speech. Unlike previous methods, in this method we first train a support vector machine (SVM) model based on feature parameters and Gaussian Mixture Model (GMM) , then integrate the language identification (LID) information based on SVM model and acoustic information into the decoding process. Lastly, we develop a prototype system to present the method. Experiments proved that our method we can improve the accurancy of code-switching speech recognition at a certain degree compared with previous methods.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 756-759)

Pages:

3622-3627

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.756-759.3622

Citation:

Cite this paper

Online since:

September 2013

Authors:

Hong Ji Zhang

Keywords:

Acoustic Model, Code-Switching Speech, Language Identification, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] B. H. Chan, Code-mixing in Hong Kong Cantonese-English bilinguals: Constraints and process, CUHK Papers in Linguistics, 4, pp.1-24, (1993).

Google Scholar

[2] P. Li, Spoken Word Recognition of Code-Switched Words by Chinese-English Bilinguals, Journal of Memory and Language. 35, pp.757-774, 1996. Article in a conference proceedings.

DOI: 10.1006/jmla.1996.0039

Google Scholar

[3] P. C. Ching, et al., From phonology and acoustic properties to automatic recognition of Cantonese, ISSIPNN- 94, Hong Kong, pp.127-132, (1994).

Google Scholar

[4] K.F. Chow, T. Lee and P.C. Ching, Sub-syllable acoustic modeling for Cantonese speech recognition, Proc. Of ISCSLP 1998, Singapore, pp.327-342, (1998).

Google Scholar

[5] P. Fung, X. H. Liu, and C. S. Cheung, Mixed language Query Disambiguation, Proc. Of ACL 1999, Maryland, pp.333-340, (1999).

Google Scholar

[6] J. Y. C. Chan, et al., Detection of Language Boundary in Code-switching utterances by Bi-phone Probabilities, ISCSLP 2004, Hong Kong, pp.293-296, (2004).

Google Scholar

[7] C. J. Shia, Y. H. Chiu and C. H. Wu, Language Boundary Detection and Identification of Mixed-Language Speech Based on MAP Estimation, ICASSP, Montreal, Vol. 1 pp.381-384, (2004).

DOI: 10.1109/icassp.2004.1326002

Google Scholar

[8] D. C. Lyu, R. Y. Lyu and C. N. Hsu, Speech recognition on code-switching among the Chinese dialects, ICASSP, Toulouse, Vol. 1 pp.1105-1108, (2006).

DOI: 10.1109/icassp.2006.1660218

Google Scholar

[9] S. R. You , et al. , Chinese-English mixed-lingual keyword spotting, ISCSLP 2004, Hong Kong, pp.237-240, (2004).

Google Scholar

[10] http: /www. speech. cs. cmu. edu/tools/lmtool. html.

Google Scholar