High quality Arabic text-to-speech synthesis using unit selection

被引：0

作者：

Abdelmalek, Raja ^{[1
]}

Mnasri, Zied ^{[1
]}

机构：

[1] Univ Tunis El Manar, ENIT, Signal Image & Technol Informat Lab, Tunis, Tunisia

来源：

2016 13TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS & DEVICES (SSD) | 2016年

关键词：

Arabic speech synthesis; unit selection; selection cost; concatenation cost;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This work aims to develop a high quality Arabic concatenative speech synthesis system based on unit selection. The original unit selection algorithm was modified to integrate more phonological, linguistic and contextual features in order to improve the selection cost calculation from one side, and more prosodic parameters for more exact concatenation cost estimation from the other side. The subjective assessments based on MOS (Mean Opinion Score) tests and visual comparison of waveforms show satisfactory results.

引用

页码：1 / 5

页数：5

共 10 条

[1]

Andrew H. J., 1996, IEEE, V1

[2]

Demenko Grazyna, 2010, INT J SPEECH TECHNOL, V13, P85

[3]

Elshafei Moustafa, 2002, INFORM SCI, V140, P255

[4]

Henton Caroline, 2002, INT J SPEECH TECHNOL, V5, P117

[5]

Hifny Yasser, 2004, ENGINEERING

[6] Speech driven realistic mouth animation based on multi-modal unit selection [J].

Jiang, Dongmei ;

Ravyse, Ilse ;

Sahli, Hichem ;

Verhelst, Werner .

JOURNAL ON MULTIMODAL USER INTERFACES, 2008, 2 (3-4) :157-169

[7]

Malika Boudraa, 2000, ACTA ACUST UNITED AC, V86, P870

[8]

Mixdorff Hansjorg, 2003, INT J SPEECH TECHNOL, V6, P45

[9] Development of syllable-based text to speech synthesis system in Bengali [J].

Narendra, N. ;

Rao, K. ;

Ghosh, Krishnendu ;

Vempada, Ramu ;

Maity, Sudhamay .

INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2011, 14 (03) :167-181

[10]

Tokuda Keiichi, 2002, IEEE

← 1 →