Including dynamic and phonetic information in voice conversion systems
作者： Antonio Bonafonte , Alexander Kain , Jan P. H. van Santen , Helenca Duxans
DOI:
关键词:
摘要: Voice Conversion (VC) systems modify a speaker voice (source speaker) to be perceived as if another (target had uttered it. Previous published VC approaches using Gaussian Mixture Models [1] performs the conversion in frame-by-frame basis only spectral information. In this paper, two new are studied order extend GMM-based systems. First, dynamic information is used build acoustic model. So, transformation carried out according sequences of frames. Then, phonetic introduced training system. Objective and perceptual results compare performance proposed
elsevier.com
isca-speech.org参考文章(7)
A. Kain, M.W. Macon, Design and evaluation of a voice conversion algorithm based on spectral envelope mapping and residual prediction international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 813- 816 ,(2001) , 10.1109/ICASSP.2001.941039
Hideki Kashioka, Tomoki Toda, Hiromichi Kawanami, Mikiko Mashimo, Kiyohiro Shikano, Nick Campbell, Evaluation of Cross-Language Voice Conversion Using Bilingual and Non-Bilingual Databases conference of the international speech communication association. ,(2002)
Yung-Hwan Oh, Eun-Kyoung Kim, Sangho Lee, Hidden Markov Model Based Voice Conversion Using Dynamic Characteristics of Speaker conference of the international speech communication association. pp. 2519- 2522 ,(1997)
Levent M. Arslan, Oytun Türk, Subband based voice conversion. conference of the international speech communication association. ,(2002)
R. Laroia, N. Phamdo, N. Farvardin, Robust and efficient quantization of speech LSP parameters using structured vector quantizers international conference on acoustics, speech, and signal processing. pp. 641- 644 ,(1991) , 10.1109/ICASSP.1991.150421
D. Sundermann, H. Ney, H. Hoge, VTLN-based cross-language voice conversion ieee automatic speech recognition and understanding workshop. pp. 676- 681 ,(2003) , 10.1109/ASRU.2003.1318521
A. Kain, M.W. Macon, Spectral voice conversion for text-to-speech synthesis international conference on acoustics speech and signal processing. ,vol. 1, pp. 285- 288 ,(1998) , 10.1109/ICASSP.1998.674423