In this paper, we describe an experimental telephone based system that recognizes speaker-independent isolated words. The recognition method is based on discrete HMMs. We apply the following new techniques to the conventional discrete HMM method; interpolation of observation probabilities using Fuzzy Vector Quantization, multiple model construction, model training using expanded speech end-points, and state duration control using Gaussian windows. Experiments are carried out on Japanese digits spoken by 269 speakers (238 for training, 31 for evaluation). An improvement of about 4.5% in recognition accuracy is obtained with the new techniques.
Cite as: Imamura, A., Hamada, H., Nakatsu, R. (1989) Speaker-independent word recognition through telephone networks using hidden Markov models. Proc. First European Conference on Speech Communication and Technology (Eurospeech 1989), 1171-1174, doi: 10.21437/Eurospeech.1989-54
@inproceedings{imamura89_eurospeech,
author={Akihiro Imamura and Hiroshi Hamada and Ryohei Nakatsu},
title={{Speaker-independent word recognition through telephone networks using hidden Markov models}},
year=1989,
booktitle={Proc. First European Conference on Speech Communication and Technology (Eurospeech 1989)},
pages={1171--1174},
doi={10.21437/Eurospeech.1989-54}
}