Effective acoustic modeling for rate-of-speech variation in large vocabulary conversational speech recognition

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 401-404

  Zheng, Jing ^a   Franco, Horacio ^a   Stolcke, Andreas ^a  

^a SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH; VOCABULARY CONTROL;

ACOUSTIC MODEL; CONVERSATIONAL SPEECH RECOGNITION; LARGE VOCABULARY; RATE DEPENDENT; RATE INDEPENDENTS; RATE OF SPEECH; RECOGNITION SYSTEMS; WORD ERROR RATE REDUCTIONS;

SPEECH RECOGNITION;

EID: 85009146015     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Fosler-Lussier, E., and Morgan, N., "Effects of speaking rate and word frequency on pronunciations in conversational speech," Speech Communication, 29(2-4): 137-158, 1998.
2. Mirghafori, N., Fosler E., and Morgan N., "Towards robustness to fast speech in ASR," Proc. IEEE Int'l Conf. Acoust. Speech Signal Proc., Vol. 1, pp. 335-338, Atlanta, 1996.
3. Morgan, N., and Fosler, E., "Combining multiple estimators of speaking rate," Proc. IEEE Int'l Conf. Acoust. Speech Signal Proc., Vol. 2, pp. 729-732, Seattle, 1998.
4. Siegler, M.A., and Stern, R.M., "On the effects of speech rate in large vocabulary speech recognition systems," Proc. IEEE Int'l. Conf. Acoust. Speech Signal Proc., Vol. 1, pp. 612-615, Detroit, 1995.
5. Zheng, J., Franco, H., Weng, F., Sankar, A., and Bratt, H., "Word-level rate-of-speech modeling using rate-specific phones and pronunciations," Proc. IEEE Int'l Conf. Acoust. Speech Signal Proc., Vol. 3, pp. 1775-1778, Istanbul, 2000.
6. Zheng, J., Franco, H., and Stolcke A., "Modeling wordlevel rate-of-speech variation in large vocabulary conversational speech recognition," Speech Communication, 41(2-3):273-286, 2003.
7. Hain, T., "Implicit pronunciation modeling in ASR," Proc. Pronunciation Modeling and Lexicon Adaptation for Spoken Language Technology, pp. 129-134, Estes Park, 2002.
8. Saraclar, M., Nock, H., and Khundanpur, S., "Pronunciation modeling by sharing Gaussian densities across phonetic models," Computer Speech and Language, Vol. 14, pp. 137-160, 2000.
9. Digalakis, V., Monaco, P., and Murveit, H., "Genones, generalized mixture tying in continuous hidden Markov model-based speech recognizers," IEEE Trans. Acoust. Speech Signal Proc., 4(4):281-289, 1996.
10. Graciarena, M., Franco, H., Zheng, J., Vergyri, D. and Stolcke, A., "Voicing feature integration in SRI's DECIPHER LVCSR system," to appear in Proc. IEEE Int'l Conf. Acoust. Speech Signal Proc. Montreal, 2004.
11. Wang, W., Stolcke, A., and Harper M., "The use of a linguistically motivated language model in conversational speech recognition," to appear in Proc. IEEE Int'l Conf. Acousti. Speech Signal Proc. Montreal, 2004.
12. Paul, D., "Extensions to phone-state decision-tree clustering: Single tree and tagged clustering," Proc. IEEE Int'l Conf. Acoust. Speech Signal Proc., Vol. 2, pp. 1487-1490, Munich, 1997.
13. Schramm, H., and Beyerlein, P., "Discriminative optimization of the lexical model," Proc. Pronunciation Modeling and Lexicon Adaptation for Spoken Language Technology, pp. 105-110, Estes Park, 2002.
14. Kessens, J.M., Wester, M., and Strik, H., "Improving the performance of a Dutch CSR by modeling within-word and cross-word pronunciation variation," Speech Communication, 29(2-4): 193-207, 1999.