Regression Approaches to Voice Quality Control Based on One-to-Many Eigenvoice Conversion

6th ISCA Workshop on Speech Synthesis, SSW 2007

Volumn , Issue , 2007, Pages 101-106

  Ohta, Kumi ^a   Ohtani, Yamato ^a   Toda, Tomoki ^a   Saruwatari, Hiroshi ^a   Shikano, Kiyohiro ^a  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

GAUSSIAN DISTRIBUTION; QUALITY ASSURANCE; QUALITY CONTROL;

DATA SET; EIGENVOICES; GAUSSIAN MIXTURE MODEL; LOW DIMENSIONAL; PARALLEL DATA; PHYSICAL MEANINGS; SINGLE SOURCE; TARGET SPEAKER; VOICE QUALITY; VOICE QUALITY CONTROLS;

EIGENVALUES AND EIGENFUNCTIONS;

EID: 78049390735     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

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. M. Abe, “Speech morphing by gradually changing spectrum parameter and fundamental frequency,” in Proc. ICSLP 96, Oct. 1996, Vol. 4, pp. 2235-2238.
3. H. Banno, H. Hata, M. Morise, T. Takahashi, T. Irino, and H. Kawahara, “Implementation of realtime STRAIGHT speech manipulation system: Report on its implementation,” Acoust. Sci. & Tech., Vol. 28, No. 3, pp. 140-146, 2007.
4. 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.
5. Y. Stylianou, O. Cappe, and E. Moulines, “Continuous probabilistictransformfor voice conversion,” IEEETrans. Speech and Audio Processing, Vol. 6, No. 2, pp. 131-142, 1998.
6. T. Toda, A.W. Black, and K. Tokuda, “Spectral conversion based on maximum likelihood estimationconsidering global variance of converted parameter,” in Proc. ICASSP 2005, Mar. 2005, Vol. 1, pp. 9-12.
7. T. Toda, Y. Ohtani, and K. Shikano, “Eigenvoice conversion based on Gaussian mixture model,” in Proc. INTERSPEECH2006-ICSLP, Sep. 2006, pp. 2446-2449.
8. T. Toda, Y. Ohtani, and K. Shikano, “One-to-many and many-to-one voice conversion based on eigenvoices,” in Proc. ICASSP 2007, Apr. 2007, pp. 1249-1252.
9. R. Kuhn, J. Junqua, P. Nguyen, and N. Niedzielski,“Rapid speaker adaptation in eigenvoice space,” IEEE Trans. Speech and Audio Processing, Vol. 8, No. 6, pp. 695-707, 2000.
10. P. Kenny, G. Boulianne, and P. Dumouchel, “Maximum likelihood estimation of eigenvoices and residual variances for large vocabulary speech recognition tasks,” in Proc. ICSLP 2002, Sep. 2002, pp. 57-60.
11. K. Shichiri, A. Sawabe, T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, “Eigenvoices for HMM-based speech synthesis,” in Proc. ICSLP2002, Sep. 2002, pp. 1269-1272.
12. K. Miyanaga, T. Masuko, and T. Kobayashi, “A style control technique for HMM-based speech synthesis,” in Proc. INTERSPEECH2004-ICSLP, Oct. 2004, pp. 1437-1440.
13. M. Tachibana, T. Nose, J. Yamagishi, and T. Kobayashi, “A technique for controlling voice quality of synthetic speech using multiple regression HSMM,” in Proc. INTERSPEECH2006-ICSLP, Sep. 2006, pp. 2438-2441.
14. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, “A compact model for speaker-adaptive training,” in Proc. ICSLP 96, Oct. 1996, Vol. 2, pp. 1137-1140.
15. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, “Speaker adaptive training for voice conversion based on eigenvoice,” IEICE Tech. Rep., SP2006-40, pp. 31-36, 2006 [in Japanese].
16. JNAS: Japanese Newspaper Article Sentences. http://www.mibel.cs.tsukuba.ac.jp/jnas/instruct.html
17. H. Kido, and H. Kasuya, “Extraction of everyday expression associated with voice quality of normal utterance,” J. Acoust. Soc. Jpn., Vol. 55, No. 6, pp. 405-411, 1999 [in Japanese].
18. H. Kido, and H. Kasuya, “Everyday expressions associated with voice quality of normal utterance —Extraction by perceptual evaluation—,” J. Acoust. Soc. Jpn., Vol. 57, No. 5, pp. 337-344, 2001 [in Japanese].
19. H. Kawahara, I. Masuda-Katsuse, and A.de Cheveigné, “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 Communication, Vol. 27, No. 3-4, pp. 187-207, 1999.