Tandem connectionist feature extraction for conversational speech recognition

Lecture Notes in Computer Science

Volumn 3361, Issue , 2005, Pages 223-231

  Zhu, Qifeng ^a   Chen, Barry ^a,b   Morgan, Nelson ^a,b   Stolcke, Andreas ^a,c  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

^c SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; FEATURE EXTRACTION; LARGE SCALE SYSTEMS; MATHEMATICAL TRANSFORMATIONS; SPEECH RECOGNITION;

GAUSSIAN-HMM; HUB-5 EVALUATION SET; MULTI-LAYER PERCEPTRONS (MLP); SWITCHBOARD CORPUS;

NEURAL NETWORKS;

EID: 24144487688     PISSN: 03029743     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-3-540-30568-2_19     Document Type: Conference Paper

References (14)

1. Andreou, A., Kamm, T., and Cohen, J., "Experiments in Vocal Tract Normalization," Proc. CAIP Workshop: Frontiers in Speech Recognition II, 1994.
2. Benitez, C., Burget, L., Chen, B., Dupont, S., Garudadri, H., Hermanskey, H., Jain, P., Kajarekar, S., Morgan, N., and Sivadas, S., "Robust ASR front-end using spectral based and discriminant features: experiments on the Aurora task", Eurospeech 2001.
3. Bourlard, H., and Wellekens, C., "Links between Markov models and multilayer perceptrons," IEEE Trans. Pattern Anal. Machine Intell. 12:1167-1178, 1990.
4. Chen, B., Zhu, Q., Morgan, N. "Learning long term temporal features in LVCSR using neural networks", submitted to ICSLP 2004.
5. Gales, M.J.F., "Semi-tied covariance matrices for hidden Markov models", IEEE Trans. Speech and Audio Processing, vol 7, pp. 272-281, 1999.
6. Gao, X., Zhu, W., and Shi, Q., "The IBM LVCSR System Used for 1998 Mandarin Broadcast News Transcription Evaluation", Proc. DARPA Broadcast News Workshop, 1999.
7. Hermansky, H., Ellis, D.P.W. and Sharma, S. "Tandem connectionist feature extraction for conventional HMM systems", Proc. ICASSP 2000, pp. 1635-1638.
8. Hermansky, H., and Sharma, S., "TRAPS - Classifiers of Temporal Patterns", in Proc. ICSLP 1998.
9. Misra, H., Bourlard, H., and Tyagi, V., "New entropy based combination rules in HMM/ANN multi-stream ASR", in Proc. ICASSP, 2003.
10. Morgan, N. and Bourlard, H., "Continuous speech recognition", IEEE Signal Processing Magazine, vol. 12, no. 3, pp. 24, May 1995.
11. Morgan, N., Chen, B., Zhu, Q. and Stolcke, A., "TRAPping Conversational Speech: Extending TRAP/Tandem approaches to conversational telephone speech recognition", ICASSP 2004.
12. Reyes-Gomez, M. and Ellis, D.P.W, "Error visualization for Tandem acoustic modeling on the Aurora task", ICASSP 2002.
13. Robinson, A.J., Cook, G.D., Ellis, D.P.W., Fosler-Lussier, E., Renals, S.J., and Williams D.A.G., "Connectionist speech recognition of Broadcast News", Speech Communication, vol. 37, no. 1-2, pp. 27-45. 2002
14. Stolcke, A., Bratt, H., Butzberger, J., Franco, H., Rao Gadde V.R., Plauche, M., Richey, C., Shriberg, E., Sonmez, K., Weng, F., and Zheng, J., "The SRI March 2005 Hub-5 conversational speech transcription system", Proc. NIST Transcription Workshop 2000.