Deterministic annealing based training algorithm for Bayesian speech recognition

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 680-683

  Shiota, Sayaka ^a   Hashimoto, Kei ^a   Nankaku, Yoshihiko ^a   Tokuda, Keiichi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Cross validation; Deterministic annealing; Speech recognition; Variational Bayesian method

Indexed keywords

BAYESIAN; BAYESIAN METHODS; CONVENTIONAL METHODS; CROSS VALIDATION; DETERMINISTIC ANNEALING; DETERMINISTIC ANNEALING EM ALGORITHMS; EM ALGORITHMS; LATENT VARIABLE; LOCAL MAXIMUM; MODEL PARAMETERS; PREDICTIVE DISTRIBUTIONS; STATE SEQUENCES; STATISTICAL TECHNIQUES; TRAINING ALGORITHMS; VARIATIONAL BAYESIAN;

ALGORITHMS; ARRAY PROCESSING; BAYESIAN NETWORKS; RAPID THERMAL ANNEALING; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 70450194713     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. N. Ueda and R. Nakano, "Deterministic Annealing EM Algorithm, " Neural Networks, (11), pp.271-282, 1998.
2. Y. Itaya, H. Zen, Y. Nankaku, C. Miyajima, K. Tokuda, and T. Kitamura, "Deterministic Annealing EM Algorithm in Parameter Estimation for Acoustic Model," IE-ICE Trans. Inf. & Syst., vol.E88-D, no.3, pp.425-431, 2005.
3. H. Attias, "Inferring parameters and structure of latent variable models by variational Bayes," in Proc. UAI 15, 1999.
4. K. Hashimoto, H. Zen, Y. Nankaku, A. Lee, and K. Tokuda, "Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition," in Proc. Interspeech, pp.936-939, 2008.
5. S. Watanabe, Y. Minami, A. Nakamura and N. Ueda "Variational Bayesian estimation and clustering for speech recognition," IEEE Trans. SAP, vol.12, pp.365-381, 2004.
6. K. Shinoda and T. Watanabe, "Acoustic Modeling Based on the MDL Criterion for speech recognition," in Proc. of Eurospeech, pp.99-102, 1997.
7. S. Shiota, K. Hashimoto, Y. Nankaku, A. Lee, K. Tokuda, "Acoustic Modeling Based on Model Structure Annealing for Speech Recognition," in Proc. Interspeech, pp.932-935, 2008.