DocumentCode :
1097088
Title :
Automatic Phonetic Segmentation by Score Predictive Model for the Corpora of Mandarin Singing Voices
Author :
Lin, Cheng-Yuan ; Jang, Jyh-Shing Roger
Author_Institution :
Nat. Tsing Hua Univ., Hsinchu
Volume :
15
Issue :
7
fYear :
2007
Firstpage :
2151
Lastpage :
2159
Abstract :
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.
Keywords :
hidden Markov models; speech processing; speech synthesis; HMM; Mandarin singing voice corpus; automatic phonetic segmentation; corpus-based singing voice synthesis; dynamic time warping; hidden Markov model; phoneme boundaries; score predictive model; support vector regression; Cepstral analysis; Computer science; Hidden Markov models; Humans; Mel frequency cepstral coefficient; Neural networks; Predictive models; Scanning probe microscopy; Speech synthesis; Viterbi algorithm; Automatic phonetic segmentation; boundary refinement; score predictive model (SPM); singing voice synthesis;
fLanguage :
English
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1558-7916
Type :
jour
DOI :
10.1109/TASL.2007.902051
Filename :
4291605
Link To Document :
بازگشت