An evaluation of Mongolian data-driven Text-to-Speech

Author

Altangerel, Chagnaa ; Purev, Jaimai ; Yesyenbyek, Kerey ; Hansakunbuntheung, Chatchawarn

Author_Institution

Center for Res. on Language Process., Nat. Univ. of Mongolia, Ulaanbaatar, Mongolia

fYear

2013

fDate

25-27 Nov. 2013

Firstpage

1

Lastpage

4

Abstract

This paper presents a first attempt to evaluate data-driven speech synthesis of Mongolian trained on 1500-sentence female speech corpus. The speech corpus contains nearly 6 hours of Mongolian female speech that is designed to cover all Mongolian phones. The evaluation is done on two levels. In overall quality evaluation, we generated 25 sentences and asked raters about their quality based on Mean Opinion Score (MOS). The second evaluation uses Phoneme confusion test, which contains all possible phoneme set in Mongolian.

Keywords

natural language processing; quality management; speech synthesis; MOS; Mongolian data-driven text-to-speech; Mongolian phones; data-driven speech synthesis; female speech corpus; mean opinion score; phoneme confusion test; quality evaluation; Computers; Educational institutions; Speech; Speech recognition; Speech synthesis; Synthesizers; Evaluation; Mongolian; Speech corpus; Text-to-Speech Synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), 2013 International Conference

Conference_Location

Gurgaon

Type

conf

DOI

10.1109/ICSDA.2013.6709881

Filename

6709881