Study on the consistency analysis between the prosody and the spectrum for Mandarin speech

勤益科大機構典藏 > 電資學院 > 電機工程系(所) > 【電機工程系所】期刊論文 > Item 987654321/6056

請使用永久網址來引用或連結此文件: http://ir.lib.ncut.edu.tw/handle/987654321/6056

題名:	Study on the consistency analysis between the prosody and the spectrum for Mandarin speech
作者:	葉政育
貢獻者:	電機工程(學)系
日期:	2013-04
上傳時間:	2017-09-27 09:58:10 (UTC+8)
摘要:	In this work, a consistency analysis between the prosody and the spectrum for Mandarin speech is presented. Found by an inspection on the pronunciation process of human beings, the consistency can be interpreted as a close correlated relation of a warping curve between the spectrum and the prosody intra a syllable. Through three steps in the procedure of the consistency analysis, the hidden Markov model (HMM) algorithm is used firstly to decode HMM-state sequences within a syllable at the same time as to divide them into three segments. Secondly, based on a designated syllable, the vector quantisation (VQ) with the Linde-Buzo-Gray algorithm is used to train the VQ codebooks of each segment. Thirdly, the prosodic vector of each segment is encoded as an index by VQ codebooks, and then the probability of each possible path is evaluated as a prerequisite to analyse the consistency. It is demonstrated experimentally that a consistency is definitely acquired in case the syllable is located exactly in the same word. These results offer a research direction that the warping process between the spectrum and the prosody intra a syllable must be considered in a text-to-speech system to improve the speech quality. © The Institution of Engineering and Technology 2013. (22 refs)
關聯:	IET SIGNAL PROCESSING
顯示於類別:	[電機工程系(所)] 【電機工程系所】期刊論文

文件中的檔案:

沒有與此文件相關的檔案.

檢視Licence

在NCUTIR中所有的資料項目都受到原著作權保護.

資料載入中.....