Efficient integration of multiple pronunciations in a large vocabulary decoder

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

Volumn 3, Issue , 2000, Pages 1659-1662

  Schramm, Hauke ^a   Aubert, Xavier L ^a  

^a PHILIPS RESEARCH LABORATORIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

SIGNAL PROCESSING; SPEECH PROCESSING; ACOUSTICS; APPROXIMATION THEORY; CONSTRAINT THEORY; DECODING; ERROR ANALYSIS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; OPTIMIZATION; PROBABILITY; SPEECH ANALYSIS; SPEECH CODING; VECTORS;

ACOUSTIC CONTRIBUTIONS; BASELINE SYSTEMS; BROADCAST NEWS; ERROR RATE; LARGE VOCABULARY; PRIOR INFORMATION; VITERBI DECODING; WEIGHTED SUM;

DECODING; CONTINUOUS SPEECH RECOGNITION;

ERROR RATE; LANGUAGE MODEL; MULTIPLE PRONUNCIATION; PRONUNCIATION VARIANT; VITERBI DECODING; VOCABULARY DECODER; VOCABULARY SPEECH RECOGNITION;

EID: 0033693213     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.862068     Document Type: Conference Paper

References (12)

1. Michael D. Riley, "A Statistical Model For Generating Pronunciation Networks" in Proc. ICASSP, pages 737-740, Toronto, USA, May 1991.
2. B. Peskin, M. Newman, Don McAllaster, "Improvements In Recognition Of Conversational Telephone Speech" In Proc. EUROSPEECH'97, Rhodes, Greece, Sep. pages 22-25, 1997.
3. S. Wegmann, P. Zhan, I. Carp, M. Newman, J. Yamron, and L. Gillick "Dragon Systems' 1998 Broadcast News Transcription System", In Proc. DARPA Broadcast News and Transcription Workshop, Herndon, Virginia, Feb. 1999.
4. Martine Adda-Decker and Lori Lamel, "Pronunciation Variants Across Systems, Languages and Speaking Style" In Proc. ESCA Workshop "Modeling Pronunciation Variation For Automatic Speech Recognition", Rodulc, May 98.
5. K. Beulen, S. Ortmanns, A. Eiden, S. Martin, L. Welling, J. Overmann, H. Ney, "Pronunciation Modeling In The RWTH Large Vocabulary Speech Recognizer", In Proc. of the ESCA Workshop 'Modeling Pronunciation Variation For Automatic Speech Recognition', Rodulc, May 1998
6. P. Beyerlein, X. L. Aubert, R. Haeb-Umbach, M. Harris, D. Klakow, A. Wendmuth, S. Molau, M. Pitz, A. Sixtus, "The Philips/RWTH System for Transcription of Broadcast News", In Proc. DARPA Broadcast News and Transcription Workshop, Herndon, Virginia, Feb. 1999.
7. T. Fukada, T. Yoshimura and Y. Sagisaka, "Automatic Generation Of Multiple Pronunciations Based On Neural Networks And Language Statistic", In Proc. of the ESCA Workshop 'Modeling Pronunciation Variation For Automatic Speech Recognition', Rodulc, May 1998
8. Hochberg, M. M., Renals S. J. and Robinson A. J. "ABBOT: The CUED hybrid connectionist-HMM large-vocabulary recognition system" in Proc. of Spoken Language Systems Technology Workshop, ARPA, March 1994.
9. H. Ney and S. Ortmanns, "Dynamic Programming Search For Continuous Speech Recognition", In IEEE Signal Processing Magazine, Sept. 1999
10. X. L. Aubert, "One Pass Cross Word Decoding For Large Vocabularies Based On A Lexical Tree Search Organization", pages 1559-1562, Proc. EUROSPEECH, Budapest, Hungary, Sep. 1999.
11. F. Wessel, K. Macherey and R. Schlueter, "Using Word Probabilities as Confidence Measures", In Proc. ICASSP, pages 225-228, Seattle, USA, May 1998.
12. Aubert, X. and Ney, H., "Large Vocabulary Continuous Speech Recognition using Word Graphs", pp. 49-52, Proc. ICASSP, Detroit, MI, May 1995.