Robust speech recognition in noisy environments: The 2001 IBM spine evaluation system

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2002, Pages

  Kingsbury, Brian ^a   Saon, George ^a   Mangu, Lidia ^a   Padmanabhan, Mukund ^a   Sarikaya, Ruhi ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; DATABASE SYSTEMS; DECODING; FIR FILTERS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; SPEECH ANALYSIS; SPEECH CODING; SPURIOUS SIGNAL NOISE; TELEPHONE SYSTEMS; VOCODERS;

CLASS BASED LANGUAGE MODELS; DIAGNOSTIC RHYME TEST; HIDDEN MARKOV MODELS; LINEAR DISCRIMINANT ANALYSIS; MULTIPASS DECODING; SPEAKER NORMALIZATION; SPEECH IN NOISY ENVIRONMENTS EVALUATION; SPEECH SEGMENTATION;

SPEECH RECOGNITION;

EID: 17344389852     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icassp.2002.5743652     Document Type: Conference Paper

References (19)

1. Insights into spoken language gleaned from phonetic transcription of the switchboard corpus
2. The lombard sign and the role of hearing in speech
3. Le signe de l'élévation de la voix
4. Glottal airflow and transglottal air pressure measurements for male and female speakers in soft, normal, and loud voice
5. Articulatory dynamics of loud and normal speech
6. Exact alpha-beta computation in logarithmic space with application to MAP word graph construction
7. Maximum likelihood modeling with Gaussian distributions for classification
8. Semi-tied full-covariance matrices for hidden Markov models
9. Analysis of the root-cepstrum for acoustic modeling and fast decoding in speech recognition
10. Perceptual linear predictive (PLP) analysis of speech
11. Speaker normalization on conversational telephone speech
12. A compact model for speaker-adaptive training
13. Maximum likelihood non-linear transformation for environment adaptation in speech recognition systems
14. Robust methods for using context-dependent features and models in a continuous speech recognizer
15. Eliminating inter-speaker variability prior to discriminant transforms
16. Maximum likelihood linear transformations for HMM-based speech recognition
17. An empirical study of smoothing techniques for language modeling
18. Finding consensus in speech recognition: Word error minimization and other applications of confusion networks
19. Large vocabulary decoding and confidence estimation using word posterior probabilities