Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm

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

Volumn 1, Issue , 2002, Pages 837-840

  Tolba, Hesham ^a   Selouani, Sid Ahmed ^a   O’Shaughnessy, Douglas ^a  

^a INRS EMT   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; FOURIER POWER SPECTRUM; HIDDEN MARKOV MODEL TOOLKIT;

ACOUSTIC SIGNAL PROCESSING; COMPUTER SIMULATION; LINGUISTICS; MARKOV PROCESSES; VECTORS;

SPEECH RECOGNITION;

EID: 17544404143     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743869     Document Type: Article

References (9)

1. Signal modeling techniques in speech recognition
2. Perceptual linear predictive (PLP) analysis of speech
3. RASTA processing of speech
4. Space/time data-information in the ARIAL project ear model
5. Structuration des Informations Acoustiques dans le Projet ARIAL
6. The DARPA speech recognition research database: Specification and status
7. The HTK book (version 2.1.1)