Large-vocabulary speech recognition under adverse acoustic environments

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Deng, Li ^a   Acero, Alex ^a   Plumpe, Mike ^a   Huang, Xuedong ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

NOISE ABATEMENT; VOCABULARY CONTROL;

ACOUSTIC ENVIRONMENT; ADAPTIVE TRAINING ALGORITHM; ERROR RATE REDUCTION; INSERTION PROCESS; LARGE VOCABULARY SPEECH RECOGNITION; MODEL LEARNING; NOISY CONDITIONS; NONSTATIONARY;

SPEECH RECOGNITION;

EID: 85009070292     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. T. Anastasakos, et al. "A compact model for speakeradaptive training", Proc. ICSLP, 1996, pp. 1137-1140.
2. A. Acero, L. Deng, T. Kristjansson, and J. Zhang. "Noise HMM adaptation using vector Taylor series", Proc. ICSLP, 2000.
3. A. Acero. Acoustic and Environmental Robustness in Automatic Speech Recognition, Kluwer Academic 1993.
4. S. Boll. "Suppression of acoustic noise in speech using spectral subtraction", IEEE Trans. Acoustics, Speech, and Signal Processing, Vol. 27, 1979, pp. 114-120.
5. X. D. Huang, A. Acero, and H. Hon. Spoken Language Processing, Prentice Hall, 2000. Chapter 10.
6. J. Mendel. Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice Hall, 1995, pp. 167.
7. C. Rathinavalu and L. Deng. "HMM-based speech recognition using state-dependent, discriminatively derived transforms on Mel-warped DFT features", IEEE Trans. Speech and Audio Processing, 1997, pp. 243-256.
8. H. Sameti, H. Sheikhzadeh, L. Deng, and R. Brennan. HMM-based strategies for enhancement of speech embedded in nonstationary noise, IEEE Trans. Speech and Audio Processing, Vol. 6, Sept. 1998, pp. 445-455.