https://scholars.lib.ntu.edu.tw/handle/123456789/331151
標題: | Automatic phonetic segmentation by score predictive model for the corpora of mandarin singing voices | 作者: | Lin, C.-Y. JYH-SHING JANG |
關鍵字: | Automatic phonetic segmentation; Boundary refinement; Score predictive model (SPM); Singing voice synthesis | 公開日期: | 2007 | 卷: | 15 | 期: | 7 | 起(迄)頁: | 2151 - 2159 | 來源出版物: | IEEE Transactions on Audio, Speech and Language Processing | 摘要: | This paper proposes the concept of a score predictive model (SPM) that can refine the phoneme boundaries obtained by a hidden Markov model (HMM) and dynamic time warping (DTW) for a Mandarin singing voice corpus. An SPM is constructed by using support vector regression. It predicts the score of a phoneme boundary according to the boundary's 58-dimensional feature vector. The correctly identified boundaries of a singing corpus can then be used for corpus-based singing voice synthesis. Several experiments with different settings, including the use of different initial estimates, different acoustic features, and various regression approaches, were designed to verify the feasibility of the proposed approach. Experimental results demonstrate that the proposed SPM is able to effectively refine the results of the HMM and DTW. © 2006 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-64249131507&doi=10.1109%2fTASL.2007.902051&partnerID=40&md5=560bc9a6dc89609ceccb630db154f763 http://scholars.lib.ntu.edu.tw/handle/123456789/331151 |
ISSN: | 15587916 | DOI: | 10.1109/TASL.2007.902051 | SDG/關鍵字: | Acoustic features; Automatic phonetic segmentation; Boundary refinement; Dynamic Time Warping; Feature vectors; Initial estimates; Score predictive model (SPM); Singing voice synthesis; Support vector regressions; Hidden Markov models; Linguistics; Predictive control systems; Refining; Software agents |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。