A Multi-Space Distribution (MSD) approach to speech recognition of tonal languages

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 1, Issue , 2006, Pages 125-128

  Wang, Huanliang ^b   Qian, Yao ^a   Soong, Frank K ^a   Zhou, Jianlai ^a   Han, Jiqing ^b  

^a MICROSOFT RESEARCH ASIA   (China)

^b HARBIN INSTITUTE OF TECHNOLOGY   (China)

Author keywords

LVCSR; Mandarin speech recognition; MSD; Speech recognition; Tone modeling

Indexed keywords

DECISION TREES; DEEP NEURAL NETWORKS; HEURISTIC METHODS; SPEECH; SPEECH SYNTHESIS;

AUTOMATIC SPEECH RECOGNITION; HEURISTIC APPROACH; HMM-BASED SPEECH SYNTHESIS; LVCSR; MANDARIN SPEECH RECOGNITION; PROBABILITY SPACES; SPACE DISTRIBUTION; TONE MODELING;

SPEECH RECOGNITION;

EID: 44949211222     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Hirst, D. and Espesser, R., "Automatic Modeling of Fundamental Frequency Using a Quadratic Spline Function", Travaux de l'Institut de Phonétique d'Aix 15, 71-85, 1993.
2. Chen, C. J., Gopinath, R. A., Monkowski, M. D., Picheny, M. A., and Shen, K., "New Methods in Continuous Mandarin Speech Recognition", In Proc. Eurospeech 1997, 1543-1546, 1997.
3. Chang, E., Zhou, J. L., Di, S., Huang, C., and Lee, K-F., "Large Vocabulary Mandarin Speech Recognition with Different Approach in Modeling Tones", In Proc. ICSLP 2000, 983-986, 2000.
4. Freij, G. J. and Fallside, F., "Lexical Stress Recognition Using Hidden Markov Models", in Proc. ICASSP 1988, 135-138, 1988.
5. Ho, T. H., Liu, C. J., Sun, H., Tsai, M. Y., and Lee, L. S., "Phonetic State Tied-Mixture Tone Modeling For Large Vocabulary Continuous Mandarin Speech Recognition", In Proc. EuroSpeech 1999, 883-886, 1999.
6. Seide, F. and Wang, N. J. C., "Two-stream Modeling of Mandarin Tones", In Proc. ICSLP 2000, 495-498, 2000.
7. Qian, Y., Soong, F. K., and Lee, T., "Tone-enhanced Generalized Character Posterior Probability (GCPP) for Cantonese LVCSR", In Proc. ICASSP 2006.
8. Lin, C. H., Wu, C. H., Ting, P. Y., and Wang, H. M., "Frameworks for Recognition of Mandarin Syllables with Tones Using Sub-syllabic Units", Journal of Speech Communication, 18(2):175-190. 1996.
9. Qian, Y., "Use of Tone Information in Cantonese LVCSR Based on Generalized Character Posterior Probability Decoding", PhD. Thesis, CUHK, 2005.
10. Tokuda, K., Masuko, T., Miyazaki, N., and Kobayashi, T., "Multi-space Probability Distribution HMM", IEICE Trans. Inf. & Syst., E85-D(3): 455-464, 2002.
11. Huang, C., Shi, Y., Zhou, J. L., Chu, M., Wang, T., and Chang, E., "Segmental Tonal Modeling for Phone Set Design in Mandarin LVCSR", In Proc. ICASSP 2004, 901-904, 2004.
12. Zhou, J. L., Tian, Y., Shi, Y., Huang, C., and Chang, E., "Tone Articulation Modeling for Mandarin Spontaneous Speech Recognition", In Proc. ICASSP 2004, 997-1000, 2004.
13. Shinoda, K. and Watanabe, T., "Acoustic Modeling Based on The MDL Principle for Speech Recognition", In Proc. EuroSpeech 1997, 99-102, 1997.