论文信息 - Hybrid SVM/HMM architectures for speech recognition

Hybrid SVM/HMM architectures for speech recognition

In this paper, we describe the use of a powerful machine learning scheme, Support Vector Machines (SVM), within the framework of hidden Markov model (HMM) based speech recognition. The hybrid SVM/HMM system has been developed based on our public domain toolkit. The hybrid system has been evaluated on the OGI Alphadigits corpus and performs at 11.6% WER, as compared to 12.7% with a triphone mixture-Gaussian HMM system, while using only a fifth of the training data used by triphone system. Several important issues that arise out of the nature of SVM classifiers have been addressed. We are in the process of migrating this technology to large vocabulary recognition tasks like SWITCHBOARD.

[1] John Platt,et al. Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[2] Steve Austin,et al. Speech recognition using segmental neural nets , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3] R. Okafor. Maximum likelihood estimation from incomplete data , 1987 .

[4] Joseph Picone,et al. Support vector machines for speech recognition , 1998, ICSLP.

[5] N. Deshmukh,et al. HIERARCHICAL SEARCH FOR LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION1 , 1999 .

[6] J. Picone,et al. Continuous speech recognition using hidden Markov models , 1990, IEEE ASSP Magazine.

[7] N. Deshmukh,et al. Hierarchical search for large-vocabulary conversational speech recognition: working toward a solution to the decoding problem , 1999 .

[8] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9] Vladimir Cherkassky,et al. The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.