Uncertainty decoding with splice for noise robust speech recognition

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

Volumn 1, Issue , 2002, Pages

  Droppo, Jasha ^a   Acero, Alex ^a   Deng, Li ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; DECODING; MATHEMATICAL MODELS; NOISE ABATEMENT; PROBABILITY DENSITY FUNCTION; PROBABILITY DISTRIBUTIONS; VECTORS;

CEPSTRAL SMOOTHING TECHNIQUE; GAUSSIAN EVALUATION; NOISE REMOVAL; STEREO PIECEWISE LINEAR COMPENSATION FOR ENVIRONMENT;

SPEECH RECOGNITION;

EID: 0036291376     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icassp.2002.5743653     Document Type: Conference Paper

References (8)

1. Large vocabulary speech recognition under adverse acoustic environments
2. On second-order statistics and linear estimation of cepstral coefficients
3. Frequency-domain maximum likelihood estimation for automatic speech recognition in additive and convolutive noises
4. Evaluation of the SPLICE algorithm on the Aurora2 database (web update)
5. Robust automatic speech recognition with missing and unreliable acoustic data
6. Robust ASR based on clean speech models: An evaluation of missing data techniques for connected digit recognition in noise
7. Efficient on-line acoustic environment estimation for FCDCN in a continuous speech recognition system
8. The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions