Extraction of pitch register from expressive speech in Japanese

Abstract

Human uses intonation to make focal prominence to give emphasis that highlights the focus of speech. Automatic extraction of proper intonation features from a speech corpus is desirous for processing speech prosody, especially in the context of speech synthesis. This paper presents a method to extract pitch register from observed F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> contours for this purpose. The method utilizes a constrained tone transformation technique under an assumption that lexical accents are confined to parallel high and low tone lines with a limited constant span. Consequently, the extracted pitch register captures dynamic range variation of the pitch accents of an utterance. The method is evaluated by objective tests upon a large-scale expressive speech corpus. A finding is that proper intonation manifested in pitch register in Japanese is very comparable with English intonation in the sense of structural form.