Synthesizing various speaking styles in a text-to-speech system

Research output: Contribution to journalArticle

Abstract

To enhance the performance of text-to-speech systems (TTS), we generated various speaking styles. As the first trial, we selected three speaking styles appropriate for task specific texts, and analyzed their characteristics. Large differences were found in the 1st and 3rd formant frequencies, fundamental frequency range and phrase height assignments, speaking rate, and segmental duration of phrases followed by pauses. Rules for making the characteristics of the speaking styles were integrated into a conventional TTS system, and listening tests confirmed the good performance of the rules.

Original languageEnglish
Pages (from-to)1019-1025
Number of pages7
JournalNTT R and D
Volume45
Issue number10
Publication statusPublished - 1996
Externally publishedYes

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Synthesizing various speaking styles in a text-to-speech system. / Abe, Masanobu.

In: NTT R and D, Vol. 45, No. 10, 1996, p. 1019-1025.

Research output: Contribution to journalArticle

@article{fa0446f5c0f740e0a3b284e9bf21f837,
title = "Synthesizing various speaking styles in a text-to-speech system",
abstract = "To enhance the performance of text-to-speech systems (TTS), we generated various speaking styles. As the first trial, we selected three speaking styles appropriate for task specific texts, and analyzed their characteristics. Large differences were found in the 1st and 3rd formant frequencies, fundamental frequency range and phrase height assignments, speaking rate, and segmental duration of phrases followed by pauses. Rules for making the characteristics of the speaking styles were integrated into a conventional TTS system, and listening tests confirmed the good performance of the rules.",
author = "Masanobu Abe",
year = "1996",
language = "English",
volume = "45",
pages = "1019--1025",
journal = "NTT R and D",
issn = "0915-2326",
publisher = "Telecommunications Association",
number = "10",

}

TY - JOUR

T1 - Synthesizing various speaking styles in a text-to-speech system

AU - Abe, Masanobu

PY - 1996

Y1 - 1996

N2 - To enhance the performance of text-to-speech systems (TTS), we generated various speaking styles. As the first trial, we selected three speaking styles appropriate for task specific texts, and analyzed their characteristics. Large differences were found in the 1st and 3rd formant frequencies, fundamental frequency range and phrase height assignments, speaking rate, and segmental duration of phrases followed by pauses. Rules for making the characteristics of the speaking styles were integrated into a conventional TTS system, and listening tests confirmed the good performance of the rules.

AB - To enhance the performance of text-to-speech systems (TTS), we generated various speaking styles. As the first trial, we selected three speaking styles appropriate for task specific texts, and analyzed their characteristics. Large differences were found in the 1st and 3rd formant frequencies, fundamental frequency range and phrase height assignments, speaking rate, and segmental duration of phrases followed by pauses. Rules for making the characteristics of the speaking styles were integrated into a conventional TTS system, and listening tests confirmed the good performance of the rules.

UR - http://www.scopus.com/inward/record.url?scp=0030398076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030398076&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030398076

VL - 45

SP - 1019

EP - 1025

JO - NTT R and D

JF - NTT R and D

SN - 0915-2326

IS - 10

ER -