Techniques for high quality Arabic speech synthesis

被引：25

作者：

Elshafei, M

Al-Muhtaseb, H ^{[1
]}

Al-Ghamdi, M

机构：

[1] King Fahd Univ Petr & Minerals, Coll Comp Sci & Engn, Dept Comp Sci, Dhahran 31261, Saudi Arabia

[2] King Fahd Mil Coll, Riyadh, Saudi Arabia

来源：

INFORMATION SCIENCES | 2002年 / 140卷 / 3-4期

关键词：

Reading machines;

D O I：

10.1016/S0020-0255(01)00175-X

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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. (C) 2002 Elsevier Science Inc. All rights reserved.

引用

页码：255 / 267

页数：13

共 11 条

[1] ABUALYAZEED MF, 1989, P 2 C AR COMP LING K
[2] AHMED M. E., 1991, ARABIAN J SCI ENG, V16
[3] Allen J., 1987, TEXT SPEECH MITTALK
[4] ANEES I, 1990, ASWAT ARABIA
[5] Donovan R., 1996, THESIS CAMBRIDGE U E
[6] DUTOIT T, 1996, INTRO TEXT SPEECH SY
[7] AN UNRESTRICTED VOCABULARY ARABIC SPEECH SYNTHESIS SYSTEM
ELIMAM, YA
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (12): : 1829 - 1845
[8] FURUI S, 1992, ADV SPEECH SIGNAL PR
[9] LEVINSON SE, 1993, IEEE COMMUN MAG NOV, P46
[10] SPROAT R, P ICSLP 92 ALB, P563

← 1 2 →