Distinctive features for use in an automatic speech recognition system

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Volumn , Issue , 2001, Pages 1613-1616

  Eide, Ellen ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH; SPEECH COMMUNICATION;

AUTOMATIC SPEECH RECOGNITION; AUTOMATIC SPEECH RECOGNITION SYSTEM; DISCRIMINATIVE FEATURES; FEATURE REPRESENTATION; SPEECH RECOGNIZER; SPEECH WAVEFORMS; WAVE FORMS; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 84871614151     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Chomsky, N. and M. Halle. "Sound Pattern of English." New York: Harper and Row. 1968.
2. Deng, L. and D. Sun. "A Statistical Approach to ASR Using Atomic Units Constructed from Overlapping Articulatory Features." Journal of the Acoustical Society of America, Volume 95. Issue 5. May, 1994. pp. 2702-2719.
3. Duda, R., P. Hart, and D. Stork. "Pattern Classification." New York: JohnWiley and Sons, Inc. 2001.
4. Eide, E. "A Linguistic Feature Representation of the Speech Waveform." PhD Thesis. Massachusetts Institute of Technology. 1993.
5. Kirchhoff, K. "Robust Speech Recognition Using Articulatory Information." International Computer Science Institute Technical Report TR-98-037. August, 1998.
6. Stevens, K. "Phonetic Features and Lexical Access." Presented at Symposium on Advanced Man-Machine Interface Through Spoken Language. November 19-22, 1988. Hawaii.