Training and adapting mlp features for arabic speech recognition

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

Volumn , Issue , 2009, Pages 4461-4464

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

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Acoustic modelling; Arabic speech recognition; Multi layer perceptron; Speaker adaptation

Indexed keywords

ACOUSTIC MODELLING; ARABIC SPEECH RECOGNITION; DISCRIMINATIVE MODELS; FEATURE ADAPTATION; MULTI-LAYER PERCEPTRON; MULTI-LAYER PERCEPTRONS; MULTI-PASS; SPEAKER ADAPTATION; WORD ERROR RATE;

ACOUSTICS; PATTERN RECOGNITION SYSTEMS; SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 70349224630     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4960620     Document Type: Conference Paper

References (11)

1. Q. Zhu, A. Stolcke, B.Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in Proc. INTERSPEECH, 2005, Lisbon.
2. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Connectionist feature extraction for conventional HMM systems," in Proc. ICASSP 2000, Istanbul.
3. G. František, P. Fousek, "Optimizing bottle-neck features for LVCSR," in Proc. ICASSP, 2008, Las Vegas.
4. R. Gemello, F. Mana, and D. Albesano, "Linear input network based speaker adaptation in the Dialogos system," in Proc. IJCNN, 1998, Anchorage.
5. M.J.F. Gales and P.C. Woodland, "Mean and variance adaptation within the MLLR framework," Computer Speech and Language, vol. 10, pp. 249-264, 1996.
6. M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, pp. 75-98, 1998.
7. P. Fousek, personal communication.
8. P. Fousek, "Extraction of features for automatic recognition of speech based on spectral dynamics," Ph.D Thesis, Czech Technical University in Prague, March 2007.
9. F. Grézl, M. Karafiát, S. Kontár, and J. Černocký, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. ICASSP, 2007, Hawaii.
10. 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. ASRU, 2007, Kyoto.
11. F. Diehl, M. J. F. Gales, M. Tomalin, & P.C. Woodland "Phonetic pronunciations for Arabic speech-to-text systems" in Proc. ICASSP, 2008, Las Vegas.