In our previous works, a Switching Linear Gaussian Hidden Markov Model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks.
Cite as: Zhu, D., Huo, Q., Wu, J. (2004) A Study of Switching State Segmentation in Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognition. Proc. International Symposium on Chinese Spoken Language Processing, 97-100
@inproceedings{zhu04b_iscslp,
author={Donglai Zhu and Qiang Huo and Jian Wu},
title={{A Study of Switching State Segmentation in Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognition}},
year=2004,
booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
pages={97--100}
}