Techniques for high quality Arabic speech synthesis

Moustafa Elshafei; Husni Al-Muhtaseb; Mansour Al-Ghamdi

doi:10.1016/S0020-0255(01)00175-X

Techniques for high quality Arabic speech synthesis

Moustafa Elshafei, Husni Al-Muhtaseb^*, Mansour Al-Ghamdi

^*Corresponding author for this work

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

43 Scopus citations

Abstract

The paper proposes a diphone/sub-syllable method for Arabic Text-to-Speech (ATTS) systems. The proposed approach exploits the particular syllabic structure of the Arabic words. For good quality, the boundaries of the speech segments are chosen to occur only at the sustained portion of vowels. The speech segments consists of consonants-half vowels, half vowel-consonants, half vowels, middle portion of vowels, and suffix consonants. The minimum set consists of about 310 segments for classical Arabic. copy; 2002 Elsevier Science Inc. All rights reserved.

Original language	English
Pages (from-to)	255-267
Number of pages	13
Journal	Information Sciences
Volume	140
Issue number	3-4
DOIs	https://doi.org/10.1016/S0020-0255(01)00175-X
State	Published - Feb 2002

Bibliographical note

Funding Information:
This work has been supported by KACST under contract number # AT-18-12. The authors would like to acknowledge also the support of KFUPM.

ASJC Scopus subject areas

Theoretical Computer Science
Software
Control and Systems Engineering
Computer Science Applications
Information Systems and Management
Artificial Intelligence

Access to Document

10.1016/S0020-0255(01)00175-X

Cite this

@article{78cac8fae88f4a208118f803b37d7b45,

title = "Techniques for high quality Arabic speech synthesis",

abstract = "The paper proposes a diphone/sub-syllable method for Arabic Text-to-Speech (ATTS) systems. The proposed approach exploits the particular syllabic structure of the Arabic words. For good quality, the boundaries of the speech segments are chosen to occur only at the sustained portion of vowels. The speech segments consists of consonants-half vowels, half vowel-consonants, half vowels, middle portion of vowels, and suffix consonants. The minimum set consists of about 310 segments for classical Arabic. copy; 2002 Elsevier Science Inc. All rights reserved.",

author = "Moustafa Elshafei and Husni Al-Muhtaseb and Mansour Al-Ghamdi",

note = "Funding Information: This work has been supported by KACST under contract number # AT-18-12. The authors would like to acknowledge also the support of KFUPM. ",

year = "2002",

month = feb,

doi = "10.1016/S0020-0255(01)00175-X",

language = "English",

volume = "140",

pages = "255--267",

journal = "Information Sciences",

issn = "0020-0255",

number = "3-4",

}

TY - JOUR

T1 - Techniques for high quality Arabic speech synthesis

AU - Elshafei, Moustafa

AU - Al-Muhtaseb, Husni

AU - Al-Ghamdi, Mansour

N1 - Funding Information: This work has been supported by KACST under contract number # AT-18-12. The authors would like to acknowledge also the support of KFUPM.

PY - 2002/2

Y1 - 2002/2

N2 - The paper proposes a diphone/sub-syllable method for Arabic Text-to-Speech (ATTS) systems. The proposed approach exploits the particular syllabic structure of the Arabic words. For good quality, the boundaries of the speech segments are chosen to occur only at the sustained portion of vowels. The speech segments consists of consonants-half vowels, half vowel-consonants, half vowels, middle portion of vowels, and suffix consonants. The minimum set consists of about 310 segments for classical Arabic. copy; 2002 Elsevier Science Inc. All rights reserved.

AB - The paper proposes a diphone/sub-syllable method for Arabic Text-to-Speech (ATTS) systems. The proposed approach exploits the particular syllabic structure of the Arabic words. For good quality, the boundaries of the speech segments are chosen to occur only at the sustained portion of vowels. The speech segments consists of consonants-half vowels, half vowel-consonants, half vowels, middle portion of vowels, and suffix consonants. The minimum set consists of about 310 segments for classical Arabic. copy; 2002 Elsevier Science Inc. All rights reserved.

UR - http://www.scopus.com/inward/record.url?scp=0036466735&partnerID=8YFLogxK

U2 - 10.1016/S0020-0255(01)00175-X

DO - 10.1016/S0020-0255(01)00175-X

M3 - Article

AN - SCOPUS:0036466735

SN - 0020-0255

VL - 140

SP - 255

EP - 267

JO - Information Sciences

JF - Information Sciences

IS - 3-4

ER -

Techniques for high quality Arabic speech synthesis

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this