Abstract

CURRENTLY, state-of-the-art speech recognition tech-nology has achieved high recognition accuracy for read texts or constrained spoken interactions. However, accuracy is still rather poor for spontaneous speech, which is not as well structured, acoustically and syntactically, as read speech. To broaden the application of speech recognition, it is, thus, crucial that the recognition performance for spontaneous speech be properly addressed. Recognition of spontaneous speech will require a paradigm shift from speech recognition to spoken language understanding. Correspondingly, there is an increasing interest in synthesizing spontaneous speech for natural conversation with computer systems. Hence, spontaneous speech processing is becoming a research area of prime importance.
This Special Issue of the IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING on the theme of Spontaneous Speech …

Date

2004

Authors

Sadaoki Furui, Mary Beckman, Julia B Hirschberg, Shuichi Itahashi, Tatsuya Kawahara, Satoshi Nakamura, S Narayanan

Journal

IEEE Transactions on Speech and Audio Processing

Volume

12

Issue

4

Pages

349-350

Publisher

IEEE