Combining multiple speech recognizers using voting and language model information

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Schwenk, Holger ^a   Gauvain, Jean Luc ^a  

^a CNRS   (France)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; ERRORS;

ERROR MEASURES; ERROR REDUCTION; EVALUATION TEST; LANGUAGE MODEL; MULTIPLE SPEECH RECOGNIZERS; ORIGINAL ALGORITHMS; SPEECH RECOGNIZER; VOTING SCHEMES;

SPEECH RECOGNITION;

EID: 84922926713     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. J. G. Fiscus. A post-processing system to yield reduced error word rates: Recognizer output voting error reduction (ROVER). In IEEE Workshop on Automatic Speech Recognition and Understanding, pages 347-354, 1997.
2. V. Goel and W. J. Byrne. Minimum Bayes-risk automatic speech recognition. Computer Speech And Language, 14(2):115-135, 2000.
3. L. Mangu, E. Brill, and A. Stolcke. Finding consensus among words: Lattice-based word error minimization. In Eurospeech, pages 495-498, 1999.
4. D. S. Pallett, J. G. Fiscus, and J. S. Garofolo. 1999 broadcast news benchmark test results. In DARPA Broadcast News Workshop, Washington, May 2000.
5. D. S. Pallett, J. G. Fiscus, J. S. Garofolo, A. Martin, and M. Przybocki. 1998 broadcast news benchmark test results: English and non-English word error rate performance measures. In DARPA Broadcast News Workshop, Hernon, VA, Feb. 1999.
6. A. Stolcke, Y. König, and M. Weintraub. Explicit word error minimization in n-best list rescoring. In Eurospeech, pages 163-165, 1997.