A hidden trajectory model with bi-directional target-filtering: Cascaded vs. integrated implementation for phonetic recognition

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

Volumn I, Issue , 2005, Pages

  Deng, Li ^a   Li, Xiang ^a   Yu, Dong ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; APPROXIMATION THEORY; ERROR CORRECTION; MAPPING; SIGNAL FILTERING AND PREDICTION;

PHONETIC RECOGNITION; TAYLOR SERIES APPROXIMATION; VOCAL TRACT RESONANCE (VTR);

SPEECH RECOGNITION;

EID: 33646762785     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415119     Document Type: Conference Paper

References (11)

1. J. Bilmes. "Graphical models and ASR," in M. Johnson, et. al.(eds.): Mathematical Foundations of Speech & Language Processing, Springer, NY, 2004, pp. 135-186.
2. J. Bridle, L. Deng, J. Picone, et. al. "An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition," Final Report, Johns Hopkins Univ. 1998, pp. 1-61.
3. L. Deng. "A dynamic, feature-based approach to the interface between phonology and phonetics for speech recognition," Speech Communication, Vol. 24, 1998, pp. 299-323.
4. L. Deng, D. Yu, and A. Acero. "A quantitative model for formant dynamics and contextually assimilated reduction in fluent speech," Proc. ICSLP, 2004, Jeju Island, Korea.
5. L. Deng, I. Bazzi, and A. Acero. "Tracking vocal tract resonances using an analytical nonlinear predictor," Proc. Eurospeech, 2003, pp. 73-76.
6. J. Frankel and S. King. "ASR - Articulatory speech recognition", Proc. Eurospeech, Vol. 1, 2001, pp. 599-602.
7. W. Holmes. "Segmental HMMs: Modeling dynamics and underlying structure in speech," in M. Johnson et. al.(eds.): Mathematical Foundations of Speech & Language Processing, Springer, NY, 2004, pp. 135-156.
8. Y. Gao, R. Bakis, J. Huang, and B. Zhang. "Multistage coarticulation model combining articulatory, formant, and cepstral features", Proc. ICSLP, Vol. 1, 2000, pp. 25-28.
9. J. Ma and L. Deng. "Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model for vocal-tract-resonance dynamics," IEEE Trans. Speech and Audio Proc., Vol.11, 2003, pp. 590-602.
10. T. Stephenson, H. Bourlard, S. Bengio, and A. Morris, "ASR using Dynamic Bayesian Networks with acoustic and articulatory variables," Proc. ICSLP, Vol. 1, 2000.
11. J. Zhou, F. Seide, and L. Deng. "Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM," IEEE Proc. ICASSP, April 2003, Vol.1, pp. 744-747.