Recent improvements to the Cambridge Arabic speech-to-text systems

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

Volumn , Issue , 2010, Pages 4382-4385

  Tomalin, M ^a   Diehl, F ^a   Gales, M J F ^a   Park, J ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Arabic; Boosted MMI; MLP features; Morphological decomposition; Speech to Text

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; LINGUISTICS;

ARABIC; BOOSTED MMI; CAMBRIDGE; INDIVIDUAL SYSTEMS; MAXIMUM MUTUAL INFORMATION; MORPHOLOGICAL DECOMPOSITION; MULTI-LAYER PERCEPTRON FEATURE; MULTILAYERS PERCEPTRONS; SPEECH-TO-TEXT; SPEECH-TO-TEXT SYSTEM;

CHARACTER RECOGNITION;

EID: 78049354759     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495641     Document Type: Conference Paper

References (17)

1. M.J.F Gales, F. Diehl, C.K. Raut, M. Tomalin, P.C. Woodland, and K. Yu, "Development of a phonetic system for large vocabulary arabic speech recognition," in Proc. of ASRU, 2007.
2. L. Nguyen, T. Ng, K. Nguyen, R. Zbib, and J. Makhoul, "Lexical and phonetic modeling for arabic automatic speech recognition," in Proc. of Interspeech, 2009.
3. F. Grézl, M. Karafiát, S. Kontár, and J. Černocký, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. of ICASSP, 2007, pp. 757-760.
4. P. Fousek, L. Lamel, and J.-L. Gauvain, "On the use of MLP features for broadcast news transcription," in Lecture Notes in Computer Science. Springer Verlag, 2008, pp. 303-310.
5. J. Park, F. Diehl, M.J.F. Gales, M. Tomalin, and P.C. Woodland, "Efficient generation and use of MLP features for arabic speech recognition," in Proc. of Interspeech, 2009.
6. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," in Proc. of ICASSP, 2000.
7. J. Park, F. Diehl, M.J.F. Gales, M. Tomalin, and P.C. Woodland, "Training and adapting MLP features for Arabic speech recognition," in Proc. of ICASSP, 2009, pp. 4461-4464.
8. F. Diehl, M.J.F. Gales, M. Tomalin, and P.C.Woodland, "Morphological analysis and decomposition for arabic speech-to-text systems," in Proc. of InterSpeech, 2009.
9. J.G. Fiscus, "A post-processing system to yield reduced word error rates: Recogniser output voting error reduction (ROVER)," in Proc. of ASRU, 2006.
10. N. Habash and O. Rambow, "Arabic tokenisation, part-of-speech tagging and morphological disambiguation in one fell swoop," in Proc. of ACL, 2005.
11. D. Vergyri, A. Mandal,W.Wang, A. Stolcke, J. Zheng, M. Graciarena, D. Rybach, C. Gollan, Schlüter R., K. Kirchhoff, A. Fari, and N. Morgan, "Development of the SRI/nightingale arabic ASR system," in Proc. of Interspeech, 2008.
12. N. Habash and F. Sadat, "Arabic preprocessing schemes for statistical machine translation," in Proc. of HLT-NAACL, 2006.
13. F. Diehl, M.J.F. Gales, M. Tomalin, and P.C. Woodland, "Phonetic pronunciations for arabic speech-to-text systems," in Proc. of ICASSP, 2008.
14. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and feature-space discriminative training," in Proc. of ICASSP, 2008.
15. G. Saon and D. Povey, "Penalty function maximization for large margin HMM training," in Proc. of Interspeech, 2008.
16. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D Thesis, University of Cambridge, 2004.
17. E. McDermott, S. Watanabe, and A. Nakamura, "Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training," in Proc. of Interspeech, 2009.