论文信息 - Improved HMM Models for High Performance Speech Recognition

Improved HMM Models for High Performance Speech Recognition

In this paper we report on the various techniques that we implemented in order to improve the basic speech recognition performance of the BYBLOS system. Some of these methods are new, while others are not. We present methods that improved performance as well as those that did not. The methods include Linear Discriminant Analysis, Supervised Vector Quantization, Shared Mixture VQ. Deleted Estimation of Context Weights, MMI Estimation Using "N-Best" Alternatives, Cross-Word Triphone Models. While we have not yet combined all of the methods in one system, the overall word recognition error rate on the May 1988 test set using the Word-Pair grammar has decreased from 3.4% to 1.7%.

[1] Mei-Yuh Hwang,et al. Recent Progress in the Sphinx Speech Recognition System , 1989, HLT.

[2] T. Kohonen,et al. Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[3] Shigeru Katagiri,et al. Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2 , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[4] Richard M. Schwartz,et al. The N-Best Algorithm: Efficient Procedure for Finding Top N Sentence Hypotheses , 1989, HLT.

[5] Jerome R. Bellegarda,et al. Tied mixture continuous parameter models for large vocabulary isolated speech recognition , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[6] Peter F. Brown,et al. The acoustic-modeling problem in automatic speech recognition , 1987 .

[7] Richard M. Schwartz,et al. A Simple Statistical Class Grammar for Measuring Speech Recognition Performance , 1989, HLT.

[8] Xuedong Huang,et al. Semi-continuous hidden Markov models for speech recognition , 1989 .

[9] Douglas B. Paul. The Lincoln Continuous Speech Recognition System: Recent Developments and Results , 1989, HLT.