Multivariate cepstral feature compensation on band-limited data for robust speech recognition

Proceedings of the 16th Nordic Conference of Computational Linguistics, NODALIDA 2007

Volumn , Issue , 2007, Pages 144-151

  Morales, Nicolas ^a   Toledano, Doroteo T ^a   Hansen, John H L ^b   Garrido, Javier ^a  

^a UNIVERSIDAD AUTÓNOMA DE MADRID   (Spain)

^b UNIVERSITY OF TEXAS AT DALLAS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BANDWIDTH;

AUTOMATIC SPEECH RECOGNITION; BANDWIDTH LIMITATION; BANDWIDTH MISMATCHES; CEPSTRAL FEATURES; FEATURE COMPENSATION; FEATURES VECTOR; LIMITED DATA; LINEAR COMBINATIONS; ROBUST SPEECH RECOGNITION; VECTOR COMPONENTS;

SPEECH RECOGNITION;

EID: 70450192316     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. H. Abut, J.H.L Hansen and K. Takeda (eds.). 2005. DSP for in-vehicle and mobile systems. Kluwer/Springer-Verlag.
2. L. Denenberg, H. Gish, M. Meteer, T. Miller, J.R. Rohlicek, W. Sadkin and M. Siu. 1993. Gisting conversational speech in real time. Proceedings ICASSP, 2: 131-134.
3. L. Deng, J. Droppo and A. Acero. 2005. Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion. IEEE Speech and Audio Processing, 13(3):412-421.
4. J. Droppo, L. Deng and A. Acero. 2001. Evaluation of the SPLICE algorithm on the Aurora2 database. Proceedings EuroSpeech, 217-220.
5. W. M. Fisher, R. Doddington and K. M. Goudie-Marshall. 1986. The DARPA Speech Recognition Research Database: Specifications and Status. Proceedings DARPA Workshop on Speech Recognition, 93-99.
6. J. H. L. Hansen, R. Huang, P. Mangalath, B. Zhou, M. Seadle, M. and J. Deller. 2004. SPEECHFIND: spoken document retrieval for a national gallery of the spoken word. NORSIG, 1-4.
7. X. Huang, A. Acero and H. W. Hon. 2001. Spoken language processing. Prentice Hall.
8. C. Jankowski, A. Kalyanswamy, S. Basson and J. Spitz. 1990. NTIMIT: A Phonetically Balanced, Continuous Speech, Telephone Bandwidth Speech Database. Proceedings of ICASSP, 1:109-112.
9. N. Morales, D. T. Toledano, J. H. L. Hansen, J. Colas and J. Garrido. 2005. Statistical class-based MFCC enhancement of filtered and band-limited speech for robust ASR. Proceedings EuroSpeech, 2629-2632.
10. N. Morales, D. T. Toledano, J. H. L. Hansen and J. Colas. 2007. Blind feature compensation for time-variant band-limited speech recognition. IEEE Signal Processing Letters, 14(1):70-73.
11. P. Moreno. 1996. Speech recognition in noisy environments. PhD. Thesis in Electrical and Computer Engineering. Carnegie Mellon University, Pittsburgh.
12. L. C. W. Pols. 1977. Spectral analysis and identification of Dutch vowels in monosyllabic words. Ph.D. Thesis. Free University of Amsterdam.
13. M. Seltzer, A. Acero and J. Droppo. 2005. Robust bandwidth extension of noise-corrupted narrowband speech. Proceedings EuroSpeech, 1509-1512.