ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition April 13-16, 2003 Tokyo Institute of Technology, Tokyo, Japan

A Corpus-Based Analysis on Prosody and Discourse Structure in Japanese Spontaneous Monologues

Kiyoko Yoneyama, Hanae Koiso, Janice Fon

The National Institute for Japanese Language, Tokyo, Japan Daito Bunka University, Japan National Taiwan Normal University, Taiwan, R.O.C.

The aim of this paper is two folds. First, the paper attempts to investigate prosody and discourse structure in Japanese spontaneous monologues by using the prosodic labels of the Corpus of Spontaneous Japanese (CSJ). The analyses of F0 peak trends and prosodic breaks confirmed previous findings in [1]. Secondly, the paper attempts to evaluate the validity of prosodic labels of the X-JToBI system that was adopted in CSJ (pitch-accents, boundary tones and break indices). The results of the analyses using three types of prosodic labels in the X-JToBI system provide evidence that the prosodic labels in CSJ can be useful for studies on discourse structures of Japanese spontaneous speech.

Reference

1. Y-J.J. Fon, A Cross-linguistic study on syntactic and discourse boundary cues in spontaneous speech, Unpublished doctoral dissertation, The Ohio State University, Columbus, OH, U.S.A., 2002.

Full Paper

Bibliographic reference.  Yoneyama, Kiyoko / Koiso, Hanae / Fon, Janice (2003): "A corpus-based analysis on prosody and discourse structure in Japanese spontaneous monologues", in SSPR-2003, paper MAO3.