Pushing the envelope - Aside

IEEE Signal Processing Magazine

Volumn 22, Issue 5, 2005, Pages 81-88

  Morgan, Nelson ^a   Zhu, Qifeng ^b   Stolcke, Andreas ^b   Sönmez, Kemal ^c   Sivadas, Sunil ^d   Shinozaki, Takahiro ^e   Ostendorf, Mari ^f   Jain, Pratibha ^g   Hermansky, Hynek ^h   Ellis, Dan ⁱ   Doddington, George ^j   Chen, Barry ^a   Çetin, Özgür ^b   Bourlard, Hervé ^k   Athineos, Marios ^l  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^c SRI INTERNATIONAL   (United States)

^d NOKIA RESEARCH CENTER   (United States)

^e University of Washington   (United States)

^f UNIVERSITY OF WASHINGTON   (United States)

^g Bangalore MMCODEC Group   (United States)

^h IDIAP RESEARCH INSTITUTE   (Switzerland)

ⁱ IDIAP Research Institute ^*  (United States)

^j NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY   (United States)

^k EPFL   (Switzerland)

^l Och Spine at New York Presbyterian Hospitals   (United States)

more..

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY; SPEECH PROCESSING; SPEECH SYNTHESIS; STATISTICAL METHODS;

AUTOMATIC SPEECH RECOGNITION; HIDDEN MARKOV MODELS; SPEECH-TO-TEXT SYSTEM; STATISTICAL MODELS;

SPEECH RECOGNITION;

EID: 85032751546     PISSN: 10535888     EISSN: None     Source Type: Journal    
DOI: 10.1109/MSP.2005.1511826     Document Type: Article

References (28)

1. J. Allen, "How do humans process and recognize speech?" IEEE Trans. Speech Audio Processing, vol. 2, no. 4, pp. 567-577, Oct. 1994.
2. B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. America, vol. 55, no. 6, pp. 1304-1312, 1974.
3. M. Athineos and D.P.W. Ellis, "Frequency-domain linear prediction for temporal features," in Proc. ASRU, 2003, pp. 261-266.
4. M. Athineos, H. Hermansky, and D. Ellis, "LP-TRAP: Linear predictive temporal patterns," in Proc. ICSLP, 2004, pp. 949-952.
5. 2: Autoregressive modeling of auditory-like 2-D spectro-temporal patterns," in Proc. ISCA Tutorial Research Workshop Statistical and Perceptual Audio Processing SAPA-04, Jeju, Korea, Oct. 2004, pp. 37-42.
6. J. Bilmes, "Maximum mutual information based reduction strategies for cross-correlation based joint distributional modeling," in Proc. ICASSP-98, Seattle, 1998, pp. 469-472.
7. H. Bourlard, H. Hermansky, and N. Morgan, "Towards increasing speech recognition error rates," Speech Commun., vol. 18, no. 3, pp. 205-231, May 1996.
8. Ö. Çetin and M. Ostendorf, "Multi-rate and variable-rate modeling of speech at phone and syllable time scales," in Proc. ICASSP 2005, pp. I-665-668.
9. B. Chen, Ö. Çetin, G. Doddington, D. Morgan M. Ostendorf, T. Shinozaki, and Q. Zhu, "A CTS task for meaningful fast-turnaround experiments" in Proc. RT-04 Workshop, IBM Palisades Center, Nov. 2004.
10. B. Chen, Q. Zhu, and N. Morgan, "Learning long term temporal features in LVCSR using neural networks," in Proc. ICSLP, 2004, pp. 612-615.
11. E. Davis and O. Selfridge, "Eyes and ears for computers," Proc. IRE, vol. 50, pp. 1093-1101, 1962.
12. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Royal Statist. Soci. Series B, vol. 39, pp. 1-38, 1977.
13. L. Deng and D. Sun, "Phonetic classification and recognition using HMM representation of overlapping articulatory features for all classes of English sounds," Proc. ICASSP, Apr. 1994, pp. 45-48.
14. H. Dudley, "The vocoder," Bell Labs Record, vol. 17, pp. 122-126, Dec. 1939.
15. R. Frost, "The road not taken," in Mountain Interval. New York: Henry Holt and Co., 1920.
16. S. Furui, "Speaker independent isolated word recognizer using dynamic features of speech spectrum," IEEE Trans. Acoust. Speech Audio Processing, vol. 34, no. 1, pp. 52-59, 1986.
17. R. Haeb-Umbach, D. Geller, and H. Ney, "Improvements in connected digit recognition using linear discriminant analysis and mixture densities," Proc. IEEE Int. Conf. Acoustics Speech Signal Processing, Adelaide, Australia, 1994, vol. 2, pp. 239-242.
18. H. Hermansky and N. Morgan, "RASTA processing of speech," IEEE Trans. Speech Audio Processing (Special Issue on Robust Speech Recognition), vol. 2, no. 4 pp. 578-589, Oct. 1994.
19. H. Hermansky and S. Sharma, "TRAPS - Classifiers of temporal patterns," in Proc. ICSLP-98, Sydney, 1998, vol. 3, pp. 1003-1006.
20. H. Hermansky, S. Sharma, and P. Jain, "Data-derived nonlinear mapping for feature extraction in HMM," in Proc. ASRU-99, Keystone, CO, 1999, pp. I-63-66.
21. M. Hunt and C. Lefebvre, "A comparison of several acoustic representations for speech recognit on with degraded and undegraded speech," in Proc. IEEE Conf. Acoustics, Speech, Signal Processing, Glasgow, Scotland, 1989, pp. 262-265.
22. M. Kleinschmidt and D. Gelbart, "Improving word accuracy with Gabor feature extraction," in Proc. ICSLP-2002, Denver, CO, Sept. 2002, pp. 25-28.
23. S. Lee and J. Glass, "Real-time probabilistic segmentation for segment-based speech recognition," in Proc. ICSLP-1998, Sydney, 1998, pp. 1803-1806.
24. M. Ostendorf, V. Digilakis, and O. Kimball, "From HMMs to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Acoustics, Speech, Signal Processing, vol. 4, no. 5, pp. 369-378, 1996.
25. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "FPME: Discriminatively trained features for speech recognition," in Proc. RT-04 Workshop, IBM Palisades Center, Nov. 2004.
26. A. Robinson, M. Hochberg, and S. Renals, "IPA: Improved modelling with recurrent neural networks," in Proc. ICASSP-94, Apr. 1994, pp. 37-40.
27. M. Sonmez, M. Plauche, E. Shriberg, and H. Franco, "Consonant discrimination in elicited and spontaneous speech: A case for signal-adaptive front ends in ASR," in Proc. ICSLP-2000, Beijing, China, Oct. 2000, pp. 548-551.
28. H. Yang, S. Van Vuuren, S. Sharma and H. Hermansky, "Relevance of time-frequency features for phonetic and speaker-channel classification," Speech Commun., vol. 31, no. 1, pp. 35-50, 2000.