5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Speaker Independent Speech Recognition Method using Constrained Time Alignment near Phoneme Discriminative Frame

Tomohiro Konuma (1), Tetsu Suzuki (1), Maki Yamada (1), Yoshio Ohno (1), Masakatsu Hoshimi (2), Katsuyuki Niyada (3)

(1) Matsushita Research Institute Tokyo, Inc., Japan
(2) Matsushita Research Institute Tokyo, Inc. Tohoku University, Japan
(3) Matsushita Electric Industrial Co.,Ltd., Japan

We present constrained time alignment acoustic models based on phonetic knowledge and a speaker independent speech recognition method using our proposed models. Japanese syllable and isolated word recognition experiments show that the models have robustness to intra- and inter- speaker varieties such as acoustic diversity. Furthermore we experiment with word recognition tests under the condition such as noise environments and endpoints free matching, it reveals the feasibility of our proposed models.

Full Paper

Bibliographic reference.  Konuma, Tomohiro / Suzuki, Tetsu / Yamada, Maki / Ohno, Yoshio / Hoshimi, Masakatsu / Niyada, Katsuyuki (1998): "Speaker independent speech recognition method using constrained time alignment near phoneme discriminative frame", In ICSLP-1998, paper 0198.