High-performance robust speech recognition using stereo training data

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

Volumn 1, Issue , 2001, Pages 301-304

  Deng, L ^a   Acero, A ^a   Jiang, L ^a   Droppo, J ^a   Huang, X ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CHANNEL DISTORTION COMPENSATION; HIGH PERFORMANCE ROBUST SPEECH RECOGNITION; MINIMUM MEAN SQUARE ERROR DECISION; ROBUST SPEECH RECOGNIZER; STEREO BASED PIECEWISE LINEAR COMPENSATION FOR ENVIRONMENT; STEREO TRAINING DATA;

ALGORITHMS; APPROXIMATION THEORY; INTEGRAL EQUATIONS; NOISE ABATEMENT; PROBABILITY; VECTOR QUANTIZATION; VECTORS;

SPEECH RECOGNITION;

EID: 0034855352     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Noise HMM adaptation using vector Taylor series for noisy speech recognition
2. Acoustic and environmental robustness in automatic speech recognition
3. Large-vocabulary speech recognition under adverse acoustic environments
4. Efficient on-line acoustic environment estimation for FCDCN in a continuous speech recognition system
5. Subword-dependent speaker clustering for improved speech recognition
6. Environment normalization for robust speech recognition using direct cepstral comparison
7. HMM-based strategies for enhancement of speech embedded in non-stationary noise