Comparison of ML, MAP, and VB based Acoustic Models in large vocabulary speech recognition

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 701-704

  Somervuo, Panu ^a  

^a AALTO UNIVERSITY   (Finland)

Author keywords

[No Author keywords available]

Indexed keywords

MAXIMUM LIKELIHOOD; VOCABULARY CONTROL;

ACOUSTIC MODEL; AUXILIARY DATA; LARGE VOCABULARY SPEECH RECOGNITION; MAXIMUM A POSTERIORI; MODEL COMPLEXITY; MODEL SELECTION; RECOGNITION ACCURACY; VARIATIONAL BAYESIAN;

SPEECH RECOGNITION;

EID: 85009144920     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Gelman, A., Carlin, J., Stern, J., Rubin, D., Bayesian Data Analysis, Chapman & Hall, 1995.
2. Attias, H., "A Variational Bayesian Framework for Graphical Models", Proc. NIPS 12, pp. 209-215, 2000.
3. Siivola, V., Hirsimäki, T., Creutz, M., Kurimo, M., "Unlimited Vocabulary Speech Recognition Based on Morphs Discovered in an Unsupervised Manner", Proc. Eurospeech 2003, pp. 2293-2296.
4. Creutz, M., Lagus, K., "Unsupervised Discovery of Morphemes", Proc. Workshop on Morphological and Phonological Learning of ACL 2002, pp. 21-30.
5. Young, S. & al., The HTK Hidden Markov Model Toolkit,
6. Kohonen, T., The Self-Organizing Map, Springer, 2001.
7. Gauvain, J., Lee, C., "Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains", IEEE Tr. SAP, Vol. 2(2):291-298, 1994.
8. Somervuo, P., "Speech Modeling using Variational Bayesian Mixture of Gaussians", Proc. ICSLP 2002, pp. 1245-1248.
9. Watanabe, S., Minami, Y., Nakamura, A., Ueda, N., "Constructing Shared-State Hidden Markov Models based on a Bayesian Approach", Proc. ICSLP 2002, pp. 2669-2672.
10. Watanabe, S., Minami, Y., Nakamura, A., Ueda, N., "Application of the Variational Bayesian Approach to Speech Recognition", Proc. NIPS 15, pp. 1261-1268, 2002.
11. Valente, F., Wellekens, C., "Variational Bayesian GMM for Speech Recognition", Proc. Eurospeech 2003, pp. 441-444.