Tandem acoustic modeling in large-vocabulary recognition

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

Volumn 1, Issue , 2001, Pages 517-520

  Ellis, Daniel P W ^a   Singh, Rita ^b   Sivadas, Sunil ^c  

^a Columbia University ^*  (United States)

^b Carnegie Mellon University   (United States)

^c OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDE MARKOV MODEL; LARGE VOCABULARY RECOGNITION; NEURAL NET PREPROCESSOR;

ACOUSTIC SIGNAL PROCESSING; MARKOV PROCESSES; NEURAL NETWORKS; PROBABILITY; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 0034848926     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940881     Document Type: Article

References (11)

1. Continuous speech recognition: An introduction to the hybrid HMM/Connectionist approach
2. Perceptually-inspired signal processing strategies for robust speech recognition in reverberant environments
3. The SPRACH system for the transcription of broadcast news
4. Nonlinear discriminant analysis for improved speech recognition
5. A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction
6. Tandem connectionist feature extraction for conventional HMM systems
7. Feature extraction using non-linear transformation for robust speech recognition on the Aurora database
8. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
9. Speech in noisy environments: Robust automatic segmentation, feature extraction, and hypothesis combination
10. Multi-stream speech recognition: Ready for prime time?
11. Tied posteriors: An approach for effective introduction of context dependency in hybrid NN/HMM LVCSR