An Evaluation of Many-to-One Voice Conversion Algorithms with Pre-Stored Speaker Data Sets

6th ISCA Workshop on Speech Synthesis, SSW 2007

Volumn , Issue , 2007, Pages 107-112

  Tani, Daisuke ^a   Ohtani, Yamato ^a   Toda, Tomoki ^a   Saruwatariand, Hiroshi ^a   Shikano, Kiyohiro ^a  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

EVC; many to one VC; SAT; speaker selection; voice conversion

Indexed keywords

DATA SET; EIGENVOICE CONVERSION; EIGENVOICES; MANY-TO-ONE; MANY-TO-ONE VOICE CONVERSION; SPEAKER ADAPTIVE TRAININGS; SPEAKER SELECTION; VOICE CONVERSION; VOICE CONVERSION ALGORITHM;

EID: 78649286010     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. H. Kuwabara, and Y. Sagisaka. Acoustic characteristics of speaker individuality control and conversion. Speech Communication, Vol. 16, No. 2, pp. 165-173, 1995.
2. A. Kain and M.W. Macon. Spectral voice conversion for text-to-speech synthesis. Proc. ICASSP, pp. 285-288, Seattle, USA, May 1998.
3. K-Y Park and H. S. Kim. Narrowband to wideband conversion of speech using GMM based transformation.Proc. ICASSP, pp. 1843-1846, 2000.
4. M. Nakagiri, T. Toda, H. Kashioka and K. Shikano. Improving body Transmitted Unvoiced Speech with Statistical Voice Conversion. Proc. INTERSPEECH2006-ICSLP, pp. 2270-2273, Pittsburgh, USA, Sep. 2006.
5. M. Abe, S. Nakamura, K. Shikano, and H. Kuwabara. Voice conversion through vector quantization. J. Acoust. Soc. Jpn. (E), Vol. 11, No. 2, pp. 71-76, 1990.
6. M. Mashimo, T. Toda, H. Kawanami, K. Shikano and N Campbell. Cross-language voice conversion using bilingual database. IPSJ Journal, Vol.43, No.7, pp.2177-2185, July 2002.
7. Y. Stylianou,O. Cappe and E.Moulines.Continuousprobabilistic transform for voice conversion. IEEE Trans. on Speech and Audio Processing, Vol. 6, no. 2, pp. 131-142, Mar. 1998.
8. T. Toda, A.W. Black and K. Tokuda. Spectral conversion based on maximum likelihood estimationconsidering global variance of converted parameter. Proc. ICASSP, pp. 9-12, 2005.
9. H. Ye and S. Young. Quality-enhanced voice morphing using maximum likelihood transformations. IEEE Trans. ASLP, Vol. 14, No. 4, pp. 1301-1312, 2006.
10. D. Sundermann, H. Hoge, A. Bonafonte, H. Ney, A. Black and S. Narayanan. Text-independent voice conversion based on unit selection. Proc. ICASSP, pp. 81-84, 2006.
11. A. Mouchtaris, J. Spiegel, and P. Mueller. Non-parallel training for voice conversion by maximum likelihood constrained adaptation. Proc. ICASSP, pp. 1-4, May. 2004
12. C.H. Lee and C.H. Wu. Map-based adaptation for speech conversion using adaptation data selection and nonparallel training. Proc. ICSLP, pp. 1164-1167, Sept. 2006.
13. T. Toda, Y. Ohtani and K. Shikano. Eigenvoice Conversion Based on Gaussian Mixture Model. Proc. ICSLP, pp. 2446-2449, Sept. 2006.
14. T. Toda, Y. Ohtani and K. Shikano. One-to-Many and Many-to-One Voice Conversion Based on Eigenvoices. Proc. ICASSP, Vol. 4, pp. 1249-1252, Apr. 2007.
15. S. Yoshizawa, A. Baba, K. Matsunami, Y. Mera, M. Yamada and K. Shikano. Unsupervised speaker adaptation based on sufficient HMM statistics of selected speakers. Proc.ICASSP2001, pp. 341-344, May 2001.
16. T. Anastasakos, J. McDonough, R. Schwartz and J. Makhoul. A compact model for speaker-adaptive training. Proc. ICSLP, Vol. 2, 1996.
17. JNAS: Japanese Newspaper Article Sentences http://www.milab.is.tsukuba.ac.jp/jnas/instruct.html
18. H. Kawahara, I. Masuda-Katsuse, and A.de Cheveigue. Restructuring speech representations using a pitch adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds. Speech Communivation, Vol. 27, No. 3-4, pp. 187-207, 1999.