A Multi-Language Speech Recognition Method Based on Confidence Bayesian Decision-Making

Abstract:

The language mixing in multi-language speech recognition is one of the hot issues of concern. After analyzing recognition problem, a method to distinguish language with re-class method according to confidence on multi-language recognition result based on Bayesian decision-making rules with minimum error rate and minimum risk was brought out. It can not only avoid cumbersome language recognition in traditional method but also achieve target of decreasing mixing cognition rate. Experiment on Chinese-English mixing recognition shows that the method can distinguish different language and improve speech recognition rate, which has practicality.

• Periodical: Advanced Materials Research (Volume 717)
• Pages: 475-480
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.717.475
• Online since: July 2013
• Authors: Yang Jie
• Keywords: Bayesian Decision-Making, Executive Degree, Multi-Language Recognition, Speech Recognition

References

[1] Zissman, M.A., Comparison of four approaches to automatic language identification of telephone speech, IEEE Trans. Speech & Audio Proc., Vol. 4, No. 1, pp.31-44, 1996.

DOI: 10.1109/tsa.1996.481450

[2] Navratil, J. 2001. Spoken Language Recognition – A Step toward Multi-linguality in Speech Processing, IEEE Trans. Speech&Audio Proc., Vol. 9, No. 6, pp.678-685, 2001.

DOI: 10.1109/89.943345

[3] Torres-Carrasquillo, P.A., Reynolds, D.A., Deller Jr., J.R., Language identification using Gaussian mixture model tokenization, IEEE ICASSP 2002, pp. I-757-760.

DOI: 10.1109/icassp.2002.1005850

[4] Chong Feng, He-yan Huang, Zhao-xiong Chen, Liang Zhang, Multiple Language Identification Based on Character-level Markov Models, Computer Science, Vol. 33, No. 1, pp.226-228, 2006.

[5] Chen-Lin Huang, Chung-Hsien Wu, Generation of phonetic units for mixed-language speech recognition based on acoustic and contextual analysis, IEEE Transactions on Computers, Vol. 56, No. 9, pp.1225-1233, 2007.

DOI: 10.1109/tc.2007.1064

[6] GARCIA E. G., MENGUSOGLU E., ERIC JANKE, Multilingual acoustic models for speech recognition in low resource devices, Acoustics, Speech and Signal Processing, pp.981-984, 2007.

DOI: 10.1109/icassp.2007.367236

[7] Hui Sun, Fang Zheng, Wen hu-Wu, Confidence scoring using context dependent features for word verification, Journal of Tsinghua University (Science and Technology), Vol. 46, No. 1, pp.94-97, 2006.

[8] Tie Ran-Zheng, Zhan Zhang, Ji Qing-Han, Keyword Spotting Based on Restricting Model and Acoustic Confidence Measure, Computer Science, Vol. 35, No. 11, pp.216-218, 2008.

[9] Bin Feng-Yan, Xiao Yan-Zhu, Zhi Jiang-Zhang, Confidence Measures and Integrating Algorithm in Utterance Verification, Vol. 17, No. 12, pp.2547-2553, 2006.

DOI: 10.1360/jos172547

[10] Bin Dong, Qing Wei-zhao, Yong Hong-Yan, Confidence measure for telephone speech recognition, Technical Acoustics, Vol. 25, No. 5, pp.473-477, 2006.

[11] METZE E., KEMP T., SCHAAJ T., Confidence measure based language identification , Acoustics, Speech, and Signal Processing, pp.1827-1830, 2000.

DOI: 10.1109/icassp.2000.862110

[12] KIM T. Y., KO H., Bayesian fusion of confidence measures for speech recognition, IEEE Signal Processing Letters, Vol. 12, No. 12, pp.871-874, 2005.

DOI: 10.1109/lsp.2005.859494

[13] Chang-Hoon, LEE Soo-Young, Noise-Robust speech recognition using top-down selective attention with an HMM classifier, IEEE Signal Processing Letters, Vol. 14, No. 7, pp.489-491, 2007.

DOI: 10.1109/lsp.2006.891326

[14] Fernández, F., R. de Córdoba, J. Ferreiros, V. Sama, L. F. D'Haro, J. Macías-Guarasa, Language Identification Techniques based on Full Recognition in an Air Traffic Control Task, pp.1565-1568, 2004.

DOI: 10.21437/interspeech.2004-37