An acoustic model for a real-time continuous phoneme recognition system must exhibit the following desirable feature: an ability to minimize the recognition performance degradation while solving the model complexity problem to confine the delay to a minimum in recognition process. To cope with the challenges, we introduce the state-dependent Phonetic Tied-Mixture (PTM) model with Head-Body- Tail (HBT) structured HMM as an acoustic model optimization. The proposed acoustic modeling method shows a significant improvement in recognition performance and becomes a solution to the sparse training data problem and the model complexity problem. Moreover, defining the exceptional Gaussian mixtures in tying process achieves a drastic reduction in phoneme error rate compared to traditional state-dependent PTM method. In this paper, we describe the new acoustic model optimization procedure and show the outstanding performance evaluation results for real-time continuous phoneme recognition system.
Cite as: Park, J., Ko, H. (2006) A new state-dependent phonetic tied-mixture model with head-body-tail structured HMM for real-time continuous phoneme recognition system. Proc. Interspeech 2006, paper 1982-Wed1BuP.9, doi: 10.21437/Interspeech.2006-443
@inproceedings{park06b_interspeech,
author={Junho Park and Hanseok Ko},
title={{A new state-dependent phonetic tied-mixture model with head-body-tail structured HMM for real-time continuous phoneme recognition system}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1982-Wed1BuP.9},
doi={10.21437/Interspeech.2006-443}
}