AUTOMATIC DATABASE STRUCTURING FOR SPEECH SYNTHESIS

홈 > 연구문헌 >

한글제목(Korean Title)	AUTOMATIC DATABASE STRUCTURING FOR SPEECH SYNTHESIS
영문제목(English Title)	AUTOMATIC DATABASE STRUCTURING FOR SPEECH SYNTHESIS
저자(Author)	Trinh Anh Tuan Youngjik Lee Sang-Hoon Kim
원문수록처(Citation)	VOL 9 NO. 01 PP. 1A ~ 0004 (1999. 04)
한글내용 (Korean Abstract)
영문내용 (English Abstract)	This paper describes the database structure of a corpus based concatenating speech synthesizer for Viet language. In our work to build a Viet language speech synthesizer we focus on two main problems The first problem is the consideration for a smooth concatenation of phoneme unit segments in syllable level and the second problem is the cross syllables co-articulation effects in term of phonological and tonal features of Viet language syllables. The features and characteristics of segmental unit in the synthesis speech database have to represent this information and to provide the ability for selection of appropriate unit in the synthesis stage. We propose an inventory structure for a synthesizer which enables a high naturalness of the synthesized speech.
키워드(Keyword)	speech synthesis Viet language speech database automatic segmentation
파일첨부	PDF 다운로드

사이트맵