8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A Prosodic Phrasing Model for a Korean Text-to-Speech Synthesis System

Kyuchul Yoon

The Ohio State University, USA

This paper presents a prosodic phrasing model for Korean to be used in a text-to-speech synthesis (TTS) system. Read text corpora were morpho-syntactically parsed and prosodically labeled following the Penn Korean Treebank (Han et al., 2002) and K-ToBI prosodic labeling conventions (Jun, 2000) respectively. Decision trees were trained with morpho-syntactic and textual distance features to predict locations of accentual and intonational phrase breaks. Our phrasing model cross-validated on a 300-sentence (6,936 words or 21,436 syllables, an average of 72 syllables or 23 words per sentence) predicted non-breaks with F=92.4% and breaks with F=88.0% (F=72.8% for accentual phrase breaks and F=71.3% for intonational phrase breaks).

Full Paper

Bibliographic reference.  Yoon, Kyuchul (2004): "A prosodic phrasing model for a Korean text-to-speech synthesis system", In INTERSPEECH-2004, 1873-1876.