ATR Japanese speech database as a tool of speech recognition and synthesis

Akira Kurematsu; Kazuya Takeda; Yoshinori Sagisaka; Shigeru Katagiri; Hisao Kuwabara; Kiyohiro Shikano

doi:10.1016/0167-6393(90)90011-W

ATR Japanese speech database as a tool of speech recognition and synthesis

Akira Kurematsu^*, Kazuya Takeda, Yoshinori Sagisaka, Shigeru Katagiri, Hisao Kuwabara, Kiyohiro Shikano

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

230 Citations (Scopus)

Abstract

A large-scale Japanese speech database has been described. The database basically consists of (1) a word speech database, (2) a continuous speech database, (3) a database for a large number of speakers, and (4) a database for speech synthesis. Multiple transcriptions have been made in five different layers from simple phonemic descriptions to fine acoustic-phonetic transcriptions. The database has been used to develop algorithms in speech recognition and synthesis studies and to find acoustic, phonetic and linguistic evidence that will serve as basic data for speech technologies.

Original language	English
Pages (from-to)	357-363
Number of pages	7
Journal	Speech Communication
Volume	9
Issue number	4
DOIs	https://doi.org/10.1016/0167-6393(90)90011-W
Publication status	Published - 1990 Aug
Externally published	Yes

ASJC Scopus subject areas

Software
Modelling and Simulation
Communication
Language and Linguistics
Linguistics and Language
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1016/0167-6393(90)90011-W

Cite this

@article{a647151f1ead47c097e90accd4c709c5,

title = "ATR Japanese speech database as a tool of speech recognition and synthesis",

abstract = "A large-scale Japanese speech database has been described. The database basically consists of (1) a word speech database, (2) a continuous speech database, (3) a database for a large number of speakers, and (4) a database for speech synthesis. Multiple transcriptions have been made in five different layers from simple phonemic descriptions to fine acoustic-phonetic transcriptions. The database has been used to develop algorithms in speech recognition and synthesis studies and to find acoustic, phonetic and linguistic evidence that will serve as basic data for speech technologies.",

author = "Akira Kurematsu and Kazuya Takeda and Yoshinori Sagisaka and Shigeru Katagiri and Hisao Kuwabara and Kiyohiro Shikano",

year = "1990",

month = aug,

doi = "10.1016/0167-6393(90)90011-W",

language = "English",

volume = "9",

pages = "357--363",

journal = "Speech Communication",

issn = "0167-6393",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - ATR Japanese speech database as a tool of speech recognition and synthesis

AU - Kurematsu, Akira

AU - Takeda, Kazuya

AU - Sagisaka, Yoshinori

AU - Katagiri, Shigeru

AU - Kuwabara, Hisao

AU - Shikano, Kiyohiro

PY - 1990/8

Y1 - 1990/8

N2 - A large-scale Japanese speech database has been described. The database basically consists of (1) a word speech database, (2) a continuous speech database, (3) a database for a large number of speakers, and (4) a database for speech synthesis. Multiple transcriptions have been made in five different layers from simple phonemic descriptions to fine acoustic-phonetic transcriptions. The database has been used to develop algorithms in speech recognition and synthesis studies and to find acoustic, phonetic and linguistic evidence that will serve as basic data for speech technologies.

AB - A large-scale Japanese speech database has been described. The database basically consists of (1) a word speech database, (2) a continuous speech database, (3) a database for a large number of speakers, and (4) a database for speech synthesis. Multiple transcriptions have been made in five different layers from simple phonemic descriptions to fine acoustic-phonetic transcriptions. The database has been used to develop algorithms in speech recognition and synthesis studies and to find acoustic, phonetic and linguistic evidence that will serve as basic data for speech technologies.

UR - http://www.scopus.com/inward/record.url?scp=0025475528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025475528&partnerID=8YFLogxK

U2 - 10.1016/0167-6393(90)90011-W

DO - 10.1016/0167-6393(90)90011-W

M3 - Article

AN - SCOPUS:0025475528

SN - 0167-6393

VL - 9

SP - 357

EP - 363

JO - Speech Communication

JF - Speech Communication

IS - 4

ER -

ATR Japanese speech database as a tool of speech recognition and synthesis

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this