Title :
Speech feature analysis and spectrum conversion from children to young adults
Author :
Xueqin Chen ; Heming Zhao ; Yibiao Yu ; Hongwei Wu
Author_Institution :
Sch. of Electron. & Inf. Eng., Soochow Univ., Suzhou, China
Abstract :
In this paper, the short time spectral envelope differences are analyzed and compared between children and young adults speech. Based on the analysis, a feature matching alignment Gaussian mixture model (FMA-GMM) is proposed to achieve the voice conversion from children to young adults. The model is gender-dependent and feature parallel training. In FMA-GMM, the F0 track matching degree is computed between several children and young adult speakers. Then a child and a young adult who have the best matching degree are chose to making feature warping alignment. The test speech is produced by twelve young people who provide the recordings in childhood. Experimental results show that the proposed method can achieve better performance than GMM and piece-wise linear warping function.
Keywords :
Gaussian processes; feature extraction; mixture models; piecewise linear techniques; spectral analysis; speech synthesis; F0 track matching degree; FMA; GMM; Gaussian mixture model; children speaker; children speech; feature matching alignment; feature parallel training; feature warping alignment; gender dependent model; piecewise linear warping function; spectral envelope difference; spectrum conversion; speech feature analysis; voice conversion; young adult speaker; young adults speech; Educational institutions; Gaussian mixture model; Speech; Speech processing; Speech recognition; Standards; Vectors; Age speech conversion; Feature matching alignment; Gaussian mixture model; Gender-dependent; Linear predictive cepstral coefficients;
Conference_Titel :
Natural Computation (ICNC), 2013 Ninth International Conference on
Conference_Location :
Shenyang
DOI :
10.1109/ICNC.2013.6818207