IMPROVED ACOUSTIC-PHONETIC MODELING IN PHILIPS' DICTATION SYSTEM BY HANDLING LIAISONS AND MULTIPLE PRONUNCIATIONS

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 767-770

  Aubert, Xavier ^a   Dugast, Christian ^a  

^a PHILIPS RESEARCH LABORATORIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNITION;

ERROR REDUCTION; INDEPENDENT TASKS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; PHILIPS; SPEAKER INDEPENDENTS; TIME-REDUCING;

SPEECH COMMUNICATION;

EID: 85135196894     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Steinbifi v., Ney H., Essen U., Tran B.-H., Aubert X., Dugast C, Kneser R., Meier H.-G., Oerder M., Haeb-Umbach R., GeUer D., HoUerbauer W., Bartosik H., "Continuous speech dictation - From theory to practice", in Speech Comm., Vol 17(1-2) pp. 1-20, August 95.
2. Aubert X., Dugast C, Ney H., Steinbiss V., "Large Vocabulary Continuous Speech Recognition of Wall Street Journal Corpus",Proc. ICASSP'94, Adelaide, AustraUa, Vol. I I, pp 129-132, 1994.
3. D u g a s t C, K n e s e r R., A u b e r t X., O r t m a n n s S., B e u l e n K., N e y H., " C o n t i n u o u s S p e e c h R e c o g n i t i o n T e s t s eind R e s u h s f o r t h e N A B ' 9 4 C o r p u s ", i n P r o c. A R P A S p o - k e n L a n g. S y s t. T e c h n. W o r k s h o p, A u s t i n, T e x a s, U S A, p p. 1 5 6 - 1 6 1, J a n u a r y 1 9 9 5.
4. Giachin E. P., Rosenberg A. E. and Lee Chin-Hui, "Word Juncture Modeling using Phonological Rules for H M M - Based continuous Speech Recognition", Comp. Speech and Lang., Vol 5, pp 155-168,1991.
5. Gauvain J. L., Lamel L. F., Eskenazi M., "Design Considerations and Text Selection for B R E F, a large French read-speech Corpus", Proc. I C S L P - 9 0, Kobe, Japan, 1990.
6. Lamel L. F., Gauvain J. L., Eskenazi M., " B R E F, a Large Vocabulary Spoken Corpus for French", Proc. E u - rospeech'91,pp. 505-508, Genova, Italy, 1991.
7. BesUng S., "A Statistical System for Grapheme-toPhoneme Conversion", Proceedings of the Tenth Annual Conference of the UW Centre for the New O E D and Text Research, pp 5-13, October 20-21, Waterloo, Ontario, Cemada, 1994.
8. Aubert X., Ney H., "Large Vocabulary Continuous Speech Recognition using Word G r a p h s ", Proc. ICASSP'95, Detroit, M I, pp 49-52, 1995.
9. Aubert X., Haeb-Umbach R. and Ney H., "Continuous Mixture Densities and Linear Discriminant Aneilysis for Improved Context-Dependent Acoustic Models", Proc. ICASSP'9S, MinneapoUs, M N, pp 648-651,1993.
10. Haeb-Umbeich R., Ney H., "Improvements in Time-Synchronous Beam Search for lODOO-Word Continuous Speech Recognition.", IEEE Trans, on Speech and Audio P r o c, Vol 2, pp 353-356, April 1994.
11. D u g a s t C, B e y e r l e i n P., H a e b - U m b a c h R., " A p p l i c a t i o n o f C l u s t e r i n g T e c h n i q u e s t o M i x t u r e D e n s i t y M o d e l i n g for C o n t i n u o u s S p e e c h R e c o g n i t i o n ", Proc. ICASSP'95, D e t r o i t (M I), U S A, M a y 9 - 1 2, 1 9 9 5.
12. Dugast C, Aubert X., Kneser R., "The Philips Large-Vocabulary Recognition System for AmericanEngUsh, French and German", this conference, Proc. E u - rospeech'95, Madrid, Spain, September 1995.