French large vocabulary recognition with cross-word phonology transducers

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

Volumn 3, Issue , 2000, Pages 1675-1678

  Boulianne, G ^a   Brousseau, J ^a   Ouellet, P ^a   Dumouchel, P ^a  

^a Cent de Recherche Informatique de Montreal   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

DECODING; DEEP NEURAL NETWORKS; SIGNAL PROCESSING; SPEECH; SPEECH PROCESSING; TRANSDUCERS; VITERBI ALGORITHM; VOCABULARY CONTROL; ALGORITHMS; ERROR ANALYSIS; FINITE AUTOMATA; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY; SPEECH CODING;

DECODING SPEED; FINITE STATE TRANSDUCERS; LARGE VOCABULARY; NETWORK SIZE; RELATIVE REDUCTION; SINGLE LEVEL; WORD CONTEXTS; WORD ERROR RATE;

SPEECH RECOGNITION; CONTINUOUS SPEECH RECOGNITION;

CROSSWORD PHONOLOGY TRANSDUCER; ERROR RATE; FRENCH LARGE VOCABULARY RECOGNITION; VITERBI ALGORITHM;

EID: 0033693374     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.862072     Document Type: Conference Paper

References (10)

1. Mohri M, "Finite-State Transducers in Language and Speech Processing", Computational Linguistics, June 1997, vol. 23, no. 2, pp. 269-312.
2. Mohri M, Riley M., Hindle D., Ljolje A., Pereira F., "Full expansion of context-dependent networks in large vocabulary speech recognition", Proc. ICASSP'98.
3. Beyerlein P., Ullrich M., Wilcox P., "Modelling and Decoding of Crossword Context Dependent Phones in the Philips Large Vocabulary Continuous Speech Recognition System", Proc. EUROSPEECH'97, vol. 3, pp. 1163-1166.
4. Aubert X., Dugast C, "Improved Acoustic-Phonetic Modelling in Philips' Dictation System by Handling Liaisons and Multiple Pronunciations", Proc. EUROSPEECHV5, vol. 1, pp. 767-770.
5. Gauvain J.-L., Lamel L. F., Adda G., and Adda-Decker M., "Speaker-independent continuous speech dictation", Proc. EUROSPEECH'93, Berlin, September 1993.
6. Valtchev V., Odell J. J., Woodland P. C. & Young S. J., "A Dynamic Network Decoder for Large Vocabulary Continuous Speech Recognition", Proc. ICSLP'94.
7. http://www.entropic.com/Support/Patches/htk.html
8. Mohri M., Pereira F., Riley M., "A Rational Design for a Weighted Finite-State Transducer Library", Lecture notes in Computer Science, p. 1436, 1998.
9. Dolmazon J. M., Bimbot F., Adda G., El Beze M., Caerou J. C., Zeiliger J., Adda-Decker M., "ARC Bl - Organisation de la première campagne AUPELF pour l'évaluation des systèmes de dictée vocale", JST97 FRANCIL, Avignon, April 97.
10. Andersen O., Kuhn R. et al., "Comparison of Two Tree-Structured Approaches for Grapheme-to-Phoneme conversion", Proc. ICSLP'96, Philadelphia, October 1996.