Heterogeneous lexical units for automatic speech recognition: Preliminary investigations

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

Volumn 3, Issue , 2000, Pages 1257-1260

  Bazzi, Issam ^a   Glass, James ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; SIGNAL PROCESSING; SPEECH; SPEECH PROCESSING; TELEPHONE SETS; ERRORS; MATHEMATICAL MODELS; SPEECH ANALYSIS; TRANSDUCERS; VOCABULARY CONTROL;

AUTOMATIC SPEECH RECOGNITION; FINITE STATE TRANSDUCERS; N-GRAM LANGUAGE MODELS; PHONETIC REPRESENTATION; SPEECH RECOGNIZER; SPEECH UNDERSTANDING; TWO-STAGE PROCESS; WEATHER INFORMATION;

SPEECH RECOGNITION;

FINITE STATE TRANSDUCER; PHONETIC ERROR RATE; WORD ERROR RATE;

EID: 0033721604     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.861804     Document Type: Conference Paper

References (5)

1. G. Chung and S. Seneff, "Improvements in speech understanding accuracy through the integration of hierarchical linguistic, prosodic, and phonological constraints in the JUPITER domain", in Proc. ICSLP, Sydney, 1998.
2. J. Glass, J. Chang, and M. McCandless, "A probabilistic framework for feature-based speech recognition", in Proc. IC-SLP, Philadelphia, PA, pp. 2277-2280, 1996.
3. J. Glass, T. Hazen, and L. Hetherington, "Real-time telephone-based speech recognition in the JUPITER domain", in Proc. ICASSP, Phoenix, AZ, 1999.
4. K. Livescu, Analysis and modeling of non-native speech for automatic speech recognition. S. M. thesis, MIT, Cambridge, August 1999.
5. J. Yi, Natural-sounding speech synthesis using variablelength units. M. Eng. thesis, MIT, Cambridge, May 1998.