Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Modeling Phone Correlation for Speaker Adaptive Speech Recognition

Baojie Li, Keikichi Hirose, Nobuaki Minematsu

School of Engineering, University of Tokyo, Bunkyo-ku, Tokyo, Japan

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.

Full Paper

Bibliographic reference.  Li, Baojie / Hirose, Keikichi / Minematsu, Nobuaki (2000): "Modeling phone correlation for speaker adaptive speech recognition", In ICSLP-2000, vol.4, 350-353.