完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Kuo, WC | en_US |
dc.contributor.author | Zhong, XR | en_US |
dc.contributor.author | Wang, YR | en_US |
dc.contributor.author | Chen, SH | en_US |
dc.date.accessioned | 2014-12-08T15:26:18Z | - |
dc.date.available | 2014-12-08T15:26:18Z | - |
dc.date.issued | 2003 | en_US |
dc.identifier.isbn | 0-7803-7663-3 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/18681 | - |
dc.description.abstract | In this paper, the implementation of a high-performance Min-Nan/Taiwanese TTS system is presented. The system can convert both Min-Nan/Taiwanese texts, represented in a hybrid Han-Lo written form, and Chinese texts into natural Taiwanese speeches. It is an improved version of the system developed previously [11]. Improvements include: the add of a "Chinese-to-Min-Nan/Taiwanese" lexicon to solve the OOV problem and to increase the ability of processing Chinese text; the use of explicit tone sandhi rules to ease the learning of prosody generation; a further processing of the training database to detect all breaks not associated with PMs; and the use of four RNNs to separately generate four types of prosodic parameters. The system is implemented by software and runs in real-time on PC. An informal subjective listening test confirmed that the system performed well. All synthetic speeches sounded natural for well-tokenized Min-Nan/Taiwanese texts and for automatic tokenized Chinese texts. | en_US |
dc.language.iso | en_US | en_US |
dc.title | A high-performance Min-Nan/Taiwanese TTS system | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.journal | 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING I | en_US |
dc.citation.spage | 512 | en_US |
dc.citation.epage | 515 | en_US |
dc.contributor.department | 電信工程研究所 | zh_TW |
dc.contributor.department | Institute of Communications Engineering | en_US |
dc.identifier.wosnumber | WOS:000185328700131 | - |
顯示於類別: | 會議論文 |