Some accentual characteristics in Japanese phrases and long compounds

Yoshinori Sagisaka, Hirokazu Sato

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper focuses on an analysis of accentual characteristics in Japanese phrases and in long compounds for the purpose of fine prosody control in Japanese text-to-speech conversion. With respect to Japanese phrase accent analysis, the secondary accent generation is shown to depend on (a) whether or not an anterior constituent word is accented, (b) phrase length and (c) the constituent word accent attributes. Moreover, the fundamental frequency patterns of phrases having a secondary accent are studied to demonstrate their systematic controllability. In terms of long compound analysis, characteristics regarding segmentation into smaller utterance groups are discussed in relation to their syntactic structure. Furthermore, their accentuation characteristics are analyzed by comparing with ordinary short compound accentuation. These results indicate the possibilities of further prosody control and the necessity for syntactic analysis for such control in Japanese text-to-speech conversion.

Original languageEnglish
Pages (from-to)65-74
Number of pages10
JournalJournal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi)
Volume7
Issue number1
DOIs
Publication statusPublished - 1986
Externally publishedYes

Fingerprint

controllability

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

@article{5092fa87a63a46d9987961a35280ee2c,
title = "Some accentual characteristics in Japanese phrases and long compounds",
abstract = "This paper focuses on an analysis of accentual characteristics in Japanese phrases and in long compounds for the purpose of fine prosody control in Japanese text-to-speech conversion. With respect to Japanese phrase accent analysis, the secondary accent generation is shown to depend on (a) whether or not an anterior constituent word is accented, (b) phrase length and (c) the constituent word accent attributes. Moreover, the fundamental frequency patterns of phrases having a secondary accent are studied to demonstrate their systematic controllability. In terms of long compound analysis, characteristics regarding segmentation into smaller utterance groups are discussed in relation to their syntactic structure. Furthermore, their accentuation characteristics are analyzed by comparing with ordinary short compound accentuation. These results indicate the possibilities of further prosody control and the necessity for syntactic analysis for such control in Japanese text-to-speech conversion.",
author = "Yoshinori Sagisaka and Hirokazu Sato",
year = "1986",
doi = "10.1250/ast.7.65",
language = "English",
volume = "7",
pages = "65--74",
journal = "Acoustical Science and Technology",
issn = "1346-3969",
publisher = "Acoustical Society of Japan",
number = "1",

}

TY - JOUR

T1 - Some accentual characteristics in Japanese phrases and long compounds

AU - Sagisaka, Yoshinori

AU - Sato, Hirokazu

PY - 1986

Y1 - 1986

N2 - This paper focuses on an analysis of accentual characteristics in Japanese phrases and in long compounds for the purpose of fine prosody control in Japanese text-to-speech conversion. With respect to Japanese phrase accent analysis, the secondary accent generation is shown to depend on (a) whether or not an anterior constituent word is accented, (b) phrase length and (c) the constituent word accent attributes. Moreover, the fundamental frequency patterns of phrases having a secondary accent are studied to demonstrate their systematic controllability. In terms of long compound analysis, characteristics regarding segmentation into smaller utterance groups are discussed in relation to their syntactic structure. Furthermore, their accentuation characteristics are analyzed by comparing with ordinary short compound accentuation. These results indicate the possibilities of further prosody control and the necessity for syntactic analysis for such control in Japanese text-to-speech conversion.

AB - This paper focuses on an analysis of accentual characteristics in Japanese phrases and in long compounds for the purpose of fine prosody control in Japanese text-to-speech conversion. With respect to Japanese phrase accent analysis, the secondary accent generation is shown to depend on (a) whether or not an anterior constituent word is accented, (b) phrase length and (c) the constituent word accent attributes. Moreover, the fundamental frequency patterns of phrases having a secondary accent are studied to demonstrate their systematic controllability. In terms of long compound analysis, characteristics regarding segmentation into smaller utterance groups are discussed in relation to their syntactic structure. Furthermore, their accentuation characteristics are analyzed by comparing with ordinary short compound accentuation. These results indicate the possibilities of further prosody control and the necessity for syntactic analysis for such control in Japanese text-to-speech conversion.

UR - http://www.scopus.com/inward/record.url?scp=85007957188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007957188&partnerID=8YFLogxK

U2 - 10.1250/ast.7.65

DO - 10.1250/ast.7.65

M3 - Article

AN - SCOPUS:85007957188

VL - 7

SP - 65

EP - 74

JO - Acoustical Science and Technology

JF - Acoustical Science and Technology

SN - 1346-3969

IS - 1

ER -