Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Frame-Period Adaptation for Speaking Rate Robust Speech Recognition

Satoru Tsuge (1), Toshiaki Fukada (1), Kenji Kita (2)

(1) Tokushima University; (2) Canon Inc.; Japan

This paper describes a frame-period adaptation method for speaking rate robust speech recognition. The proposed method determines an appropriate frame-period for each phrase by measuring its speaking rate or computing the acoustic likelihood with a set of frame-periods. Experimental results on spontaneous speech recognition show that the proposed method is effective for slower utterance. Actually, we can get about a 15% error reduction in error rate for slower utterance by using the likelihood based frame-period determination.


Full Paper

Bibliographic reference.  Tsuge, Satoru / Fukada, Toshiaki / Kita, Kenji (2000): "Frame-period adaptation for speaking rate robust speech recognition", In ICSLP-2000, vol.3, 718-721.