Information of phone relationships is regarded as acting an important role in speech recognition. It has been successfully exploited in many speaker adaptation approaches. In this paper, we propose a new approach, named Phone Pair Model (PPM) re-scoring, to utilize phone relationships for speaker-adaptive speech recognition. PPM re-scoring approach does not really adapt model parameters to a new speaker. It just uses some pre-registered phones' samples from the speaker being recognized, to re-calculate the likelihood of phones that has been calculated on conventional phone HMMs, resulting in a more correct recognition result. Additionally, it can deal with not only inter-speaker acoustic variations but also intra-speaker acoustic variations adequately. Results of two recognition experiments, one using phone HMMs only and the other incorporating phone HMMs with the PPMs, showed that even by using only a few vowel samples as the pre-registered phones, PPM re-scoring approach brought an increase in recognition rate.
Cite as: Li, B., Hirose, K., Minematsu, N. (2000) Modeling phone correlation for speaker adaptive speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 350-353, doi: 10.21437/ICSLP.2000-822
@inproceedings{li00l_icslp,
author={Baojie Li and Keikichi Hirose and Nobuaki Minematsu},
title={{Modeling phone correlation for speaker adaptive speech recognition}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 350-353},
doi={10.21437/ICSLP.2000-822}
}