Semi-parametric trajectory modelling using temporally varying feature mapping for speech recognition

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 2982-2985

  Sim, Khe Chai ^a   Liu, Shilin ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Complexity control; Conditional random field; State clustering

Indexed keywords

MAPPING; SPEECH COMMUNICATION; SPEECH SYNTHESIS; TRAJECTORIES; SPEECH RECOGNITION;

COMPLEXITY CONTROLS; CONDITIONAL RANDOM FIELD; PHONE RECOGNITION; STATE CLUSTERING; TRAJECTORY INFORMATION; TRAJECTORY MODELLING; VARYING PARAMETERS; WALL STREET JOURNAL; FEATURE MAPPING; PERFORMANCE; RANDOM FIELDS; SEMIPARAMETRIC; STATE SEQUENCES; TRAJECTORY MODELS;

SPEECH RECOGNITION; TRAJECTORIES;

EID: 79959812251     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. K. C. Sim and M. J. F. Gales, "Discriminative semiparametric trajectory model for speech recognition," Comput. Speech Lang., vol. 21, no. 4, pp. 669-687, 2007. (Pubitemid 46880192)
2. H. Zen, K. Tokuda, and T. Kitamura, "A viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features," in Proc. of ICASSP, 2004, pp. 837-840.
3. -, "An introduction of trajectory model into HMM-based speech synthesis," in Proc. of 5th ISCA Speech Synthesis Workshop, 2004.
4. K. C. Sim and M. J. F. Gales, "Minimum phone error training of precision matrix models," IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 3, pp. 882-889, 2006. (Pubitemid 46547650)
5. B. Zhang, S. Matsoukas, and R. Schwartz, "Discriminatively trained region dependent transforms for speech recognition," in Proc. of ICASSP, 2006.
6. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," in Proc. ICASSP, 2005.
7. J. Droppo and A. Acero, "Maximum mutual information SPLICE transform for seen and unseen conditions," in Proc of Interspeech, 2005.
8. D. Povey and P. C. Woodland, "Minimum Phone Error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002.
9. M. Afify, X. Cui, and Y. Gao, "Stereo-based stochastic mapping for robust speech recognition," Trans. Audio, Speech and Lang., vol. 17, no. 7, pp. 1325-1334, 2009.
10. M. J. F. Gales and P. C. Woodland, "Mean and variance adaptation within the MLLR framework," Computer Speech and Languages, vol. 10, pp. 249-264, 1996. (Pubitemid 126374488)