Text-to-speech synthesis technology using corpus-based approach

Hideyuki Mizuno, Hisako Asano, Mitsuaki Isogai, Miki Hasebe, Masanobu Abe

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Many people hope that in the future computers, machines, and robots will talk just like humans, letting us communicate with them naturally. Speech synthesis technology is an important component for this. We have developed text-to-speech synthesis technology using a corpus-based approach. This article introduces this technology, which-can produce natural synthetic speech that is just like human speech.

Original languageEnglish
Pages (from-to)70-75
Number of pages6
JournalNTT Technical Review
Volume2
Issue number3
Publication statusPublished - Mar 2004
Externally publishedYes

Fingerprint

Speech synthesis
Robots

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Mizuno, H., Asano, H., Isogai, M., Hasebe, M., & Abe, M. (2004). Text-to-speech synthesis technology using corpus-based approach. NTT Technical Review, 2(3), 70-75.

Text-to-speech synthesis technology using corpus-based approach. / Mizuno, Hideyuki; Asano, Hisako; Isogai, Mitsuaki; Hasebe, Miki; Abe, Masanobu.

In: NTT Technical Review, Vol. 2, No. 3, 03.2004, p. 70-75.

Research output: Contribution to journalArticle

Mizuno, H, Asano, H, Isogai, M, Hasebe, M & Abe, M 2004, 'Text-to-speech synthesis technology using corpus-based approach', NTT Technical Review, vol. 2, no. 3, pp. 70-75.
Mizuno H, Asano H, Isogai M, Hasebe M, Abe M. Text-to-speech synthesis technology using corpus-based approach. NTT Technical Review. 2004 Mar;2(3):70-75.
Mizuno, Hideyuki ; Asano, Hisako ; Isogai, Mitsuaki ; Hasebe, Miki ; Abe, Masanobu. / Text-to-speech synthesis technology using corpus-based approach. In: NTT Technical Review. 2004 ; Vol. 2, No. 3. pp. 70-75.
@article{6fb30516040e4d4e9f9aef209a05de43,
title = "Text-to-speech synthesis technology using corpus-based approach",
abstract = "Many people hope that in the future computers, machines, and robots will talk just like humans, letting us communicate with them naturally. Speech synthesis technology is an important component for this. We have developed text-to-speech synthesis technology using a corpus-based approach. This article introduces this technology, which-can produce natural synthetic speech that is just like human speech.",
author = "Hideyuki Mizuno and Hisako Asano and Mitsuaki Isogai and Miki Hasebe and Masanobu Abe",
year = "2004",
month = "3",
language = "English",
volume = "2",
pages = "70--75",
journal = "NTT Technical Review",
issn = "1348-3447",
publisher = "Nippon Telegraph and Telephone Corp.",
number = "3",

}

TY - JOUR

T1 - Text-to-speech synthesis technology using corpus-based approach

AU - Mizuno, Hideyuki

AU - Asano, Hisako

AU - Isogai, Mitsuaki

AU - Hasebe, Miki

AU - Abe, Masanobu

PY - 2004/3

Y1 - 2004/3

N2 - Many people hope that in the future computers, machines, and robots will talk just like humans, letting us communicate with them naturally. Speech synthesis technology is an important component for this. We have developed text-to-speech synthesis technology using a corpus-based approach. This article introduces this technology, which-can produce natural synthetic speech that is just like human speech.

AB - Many people hope that in the future computers, machines, and robots will talk just like humans, letting us communicate with them naturally. Speech synthesis technology is an important component for this. We have developed text-to-speech synthesis technology using a corpus-based approach. This article introduces this technology, which-can produce natural synthetic speech that is just like human speech.

UR - http://www.scopus.com/inward/record.url?scp=3242815347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3242815347&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:3242815347

VL - 2

SP - 70

EP - 75

JO - NTT Technical Review

JF - NTT Technical Review

SN - 1348-3447

IS - 3

ER -