Noise robust speech parameterization using multiresolution feature extraction

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 8, 2001, Pages 856-865

  Hariharan, Ramalingam ^a,b   Kiss, Imre ^a,b   Viikki, Olli ^a,b  

^a IEEE   (Finland)

^b NOKIA RESEARCH CENTER   (United States)

Author keywords

Cesptral normalization; Feature extraction; Front end; Multiband speech recognition; Multiresolution front end; Noise robust feature extraction; Noise robustness; Speech recognition; Subband speech recognition

Indexed keywords

CEPSTRAL NORMALIZATION; MULTIRESOLUTION FEATURE EXTRACTION; SPEECH PARAMETERIZATION;

ALGORITHMS; COMPUTATIONAL COMPLEXITY; FEATURE EXTRACTION; MATHEMATICAL TRANSFORMATIONS; PERFORMANCE; PRINCIPAL COMPONENT ANALYSIS; SIGNAL TO NOISE RATIO; TRANSFER FUNCTIONS;

SPEECH RECOGNITION;

EID: 0035510539     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.966088     Document Type: Article

References (33)

1. How do humans process and recognize speech?
2. A new ASR approach based on independent processing and recombination of partial frequency bands
3. Comparison of parametric representations of monosyllabic word recognition in continuously spoken sentences
4. Maximum a posteriori estimation of multivariate Gaussian mixture observations of Markov chains
5. Cepstral parameter compensation for HMM recognition
6. Multi-resolution front-end for noise robust speech recognition
7. Perceptual linear predictive (PLP) analysis of speech
8. Downsampling speech representation in ASR
9. Spectral basis functions from discriminant analysis
10. RASTA processing of speech
11. Toward ASR on partially corrupted speech
12. TRAPS - Classifiers of temporal patterns
13. Should recognizers have ears?
14. Multi-stream speech recognition: Ready for prime time?
15. Analysis of source of variability in speech
16. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
17. Experiments with a nonlinear spectral subtractor (NSS), hidden Markov models and the projection, for robust speech recognition in cars
18. A multi-band approach to automatic speech recognition
19. Combining connectionist multi-band and full-band probability streams for speech recognition of natural numbers
20. Multi-band speech recognition in noisy environments
21. Experimental framework for the evaluation of distributed speech recognition front-ends
22. Cepstral channel normalization techniques for HMM-based speaker verification
23. Analysis of acoustic-phonetic variations in fluent speech using TIMIT
24. Noise robust two-stream auditory feature extraction for noise robust speech recognition
25. Sub-band based recognition of noisy speech
26. Multiband and adaptation approaches to robust speech recognition
27. Noise robust HMM-based speech recognition using segmental cepstral feature vector normalization
28. A recursive feature vector normalization approach for robust speech recognition in noise
29. Cepstral domain segmental feature vector normalization for noise robust speech recognition
30. HTK: Tool Kit V2.1