An investigation of tied-mixture GMM based triphone state clustering

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

Volumn , Issue , 2012, Pages 4717-4720

  Wang, Guangsen ^a   Sim, Khe Chai ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

context dependent modeling; phonetic decision tree; state clustering; Tied mixture

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELING; CONTEXT DEPENDENT; DECISION TREE CLUSTERING; DISCRIMINATIVE TRAINING; GAUSSIAN MIXTURE MODEL; GAUSSIANS; MODEL COMPLEXITY; NUMBER OF STATE; PHONETIC DECISION TREE; QUESTION SELECTION; STATE CLUSTERING; STATE DISTRIBUTIONS; TIED-MIXTURE; TRIPHONES;

DECISION TREES; SIGNAL PROCESSING;

MIXTURES;

EID: 84867620524     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288972     Document Type: Conference Paper

References (11)

1. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-based state tying for high accuracy acoustic modelling," in HLT, 1994, pp. 307-312.
2. T. Ko and B. Mak, "A fully automated derivation of state-based eigentriphones for triphone modeling with no tied states using regularization," in Interspeech, 2011, pp. 781-784.
3. M. J. F. Gales and K. Yu, "Canonical state models for automatic speech recognition," in Interspeech, 2010, pp. 58-61.
4. D. Povey and L. Burget et al., "The subspace gaussian mixture model-a structured model for speech recognition," Comput. Speech Lang., vol. 25, pp. 404-439, 2011.
5. W. Chou and W. Reichl, "Decision tree state tying based on penalized Bayesian information criterion," in IEEE., ICASSP, 1999, pp. 345-348.
6. S. Watanabe, Y. Minami, A. Nakamura, and N. Ueda, "Variational Bayesian estimation and clustering for speech recognition," IEEE Trans. Speech Audio Processing, vol. 12, pp. 365-381, 2004.
7. V. Digalakis, P. Monaco, and H. Murveit, "Genones: Generalized mixture tying in continuous hidden markov model-based speech recognizers," IEEE Trans. on Speech Audio Processing, vol. 4, pp. 281-289, 1996.
8. D. Povey, Discriminative training for large vocabulary speech recognition, PhD thesis, Cambridge University, 2004.
9. T. Robinson and J. Fransen et.al, "WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition," in IEEE., ICASSP, 1995, pp. 81-84.
10. S. J. Young et al., The HTK Book, version 3.4, Cambridge University Engineering Department, Cambridge, UK, 2009.
11. H.J. Nock, M.J.F. Gales, and S.J. Young, "A comparative study of methods for phonetic decision-tree state clustering," in European Conf. on Speech Commun. & Tech., 1997, pp. 111-114.