Training wideband acoustic models using mixed-bandwidth training data for speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 1, 2007, Pages 235-245

  Seltzer, Michael L ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Acoustic modeling; Bandwidth extension; Hidden Markov models (HMMs); Speech recognition; Telephone speech

Indexed keywords

ACOUSTIC MODELING; ACOUSTIC MODELS; BANDWIDTH EXTENSION; EXPECTATION-MAXIMIZATION ALGORITHMS; HIDDEN MARKOV MODELS (HMMS); NARROW BANDS; RECOGNITION ACCURACIES; RECOGNITION SYSTEMS; SPEECH RECOGNIZERS; SUB-OPTIMAL PERFORMANCE; TELEPHONE BANDWIDTHS; TELEPHONE SPEECH; TRAINING ALGORITHMS; TRAINING DATUM; TRAINING SCHEMES; TRAINING STRATEGIES; WIDE BANDS; WIDEBAND SPEECH;

ACOUSTICS; BANDWIDTH; COMPUTATIONAL GRAMMARS; HIDDEN MARKOV MODELS; OBJECT RECOGNITION; SPEECH ANALYSIS; TELECOMMUNICATION SYSTEMS; TELEPHONE; TELEPHONE SETS; WAVELET TRANSFORMS;

SPEECH RECOGNITION;

EID: 64149084747     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.876774     Document Type: Article

References (21)

1. N. Morgan, D. Baron, S. Bhagatl, H. Carvey, R. Dhillon, J. Edwards, D. Gelbart, A. Janin, A. Krupskil, B. Peskin, T. Pfau, E. Shriberg, A. Stolcke, and C. Wooters, "Meetings about meetings: research at ICSI on speech in multiparty conversations," in Proc. ICASSP, Hong Kong, China, Apr. 2003, vol. 4, pp. 740-743.
2. J. S. Garofolo, C. D. Laprun, and J. G. Fiscus, "The rich transcription 2004 Spring meeting recognition evaluation," in Proc. NIST RT04 Meeting Recognition Workshop, Montreal, QC, Canada, May 2004.
3. P. Moreno and R. M. Stern, "Sources of degradation of speech recognition in the telephone network," in Proc. ICASSP, Adelaide, Australia, Apr. 1994, vol. I, pp. 109-112.
4. Z. Ghahramani and M. I. Jordan, "Supervised learning from incomplete data via an EM approach," Adv. Neural Inf. Proc. Sys., pp. 120-127, 1994.
5. B. Raj, M. L. Seltzer, and R. M. Stern, "Reconstruction of damaged spectrographic features for robust speech recognition," Speech Commun., vol. 43, no. 4, pp. 275-296, Sep. 2004.
6. M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Commun., vol. 34, no. 3, pp. 267-285, Jun. 2001.
7. M. L. Seltzer, B. Raj, and R. M. Stern, "Classifier-based mask estimation for missing feature methods of robust speech recognition," Speech Commun., vol. 43, no. 4, pp. 379-393, Sep. 2004.
8. L. G. Neumeyer, V. V. Digalakis, and M. Weintraub, "Training issues and channel equalization techniques for the construction of telephone acoustic models using a high-quality speech corpus," IEEE Trans. Speech Audio Process., vol. 2, no. 4, pp. 590-597, Oct. 1994.
9. Y. M. Cheng, D. O'Shaughnessy, and P. Mermelstein, "Statistical recovery of wideband speech from narrowband speech," IEEE Trans. Speech Audio Process., vol. 2, no. 4, pp. 544-548, Oct. 1994.
10. K.-Y. Park and H. S. Kim, "Narrowband to wideband conversion of speech using GMM based transformation," in Proc. ICASSP, Istanbul, Turkey, Jun. 2000, vol. 3, pp. 1843-1846.
11. P. Jax and P. Vary, "Wideband extension of telephone speech using a hidden Markov model," in IEEEWorkshop on Speech Coding, Delavan, WI, Sep. 2000, pp. 133-135.
12. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statistical Soc., vol. 39, no. 1, pp. 1-38, 1977.
13. J. M. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control. Englewood Cliffs, New Jersey: Prentice- Hall, 1995.
14. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, Feb. 1990.
15. P. C.Woodland, M. J. F. Gales, and D. Pye, "Improving environmental robustness in large-vocabulary speech recognition," in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, Atlanta, GA, May 1996, vol. 1, pp. 65-69.
16. D. B. Paul and J. M. Baker, "The design of the Wall Street Journalbased CSR corpus," in Proc. ARPA Speech Nat. Lang. Workshop, Harriman, NY, Feb. 1992, pp. 357-362.
17. S. Young, "The HTK Hidden Markov Model Toolkit: Design and Philosophy," Cambridge Univ. Tech. Rep., Cambridge, U.K., 1994.
18. M. L. Seltzer and A. Acero, "Training wideband acoustic models using mixed-bandwidth training data via feature bandwidth extension," in Proc. ICASSP, Philadelphia, PA, Mar. 2005, vol. 1, pp. 921-924.
19. C. J. Leggetter and P. C. Woodland, "Speaker Adaptation of HMMs Using Linear Regression," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR. 181, Jun. 1994.
20. J. Godfrey, E. C. Holliman, and J. McDaniel, "SWITCHBOARD: telephone speech corpus for research and development," in Proc. ICASSP, San Francisco, CA, Mar. 1992, vol. 1, pp. 517-520.
21. J. A. Bilmes, "A Gentle Tutorial of the EM Algorithm and its Applications to Parameter Estimation for Gussian Mixture and Hidden Markov Models," Univ. California, Berkeley, Berkeley, Tech. Rep. TR-97-021, Apr. 1998.