Statistical singing voice conversion based on direct waveform modification with global variance

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2015-January, Issue , 2015, Pages 2754-2758

  Kobayashi, Kazuhiro ^a   Toda, Tomoki ^a   Neubig, Graham ^a   Sakti, Sakriani ^a   Nakamura, Satoshi ^a  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

Direct waveform modification; Gaussian mixture model; Global variance; Spectral differential; Statistical singing voice conversion

Indexed keywords

GAUSSIAN DISTRIBUTION; SPEECH COMMUNICATION;

GAUSSIAN MIXTURE MODEL; GLOBAL VARIANCE; SINGING VOICES; SPECTRAL DIFFERENTIAL; WAVEFORM MODIFICATIONS;

SPEECH PROCESSING;

EID: 84959111811     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. H. Kenmochi and H. Ohshita, "VOCALOID-Commericialsinging synthesizer based on sample concatenation, " Proc. INTERSPEECH, pp. 4011-4012, Aug. 2007.
2. K. Saino, M. Tachibana, and H. Kenmochi, "A singing stylemodeling system for singing voice synthesizers. " Proc. INTERSPEECH, pp. 2894-2897, Sept. 2010.
3. K. Oura, A. Mase, T. Yamada, S. Muto, Y. Nankaku, and K. Tokuda, "Recent development of the HMM-based singingvoice synthesis system-Sinsy, " SSW7, pp. 211-216, Sept. 2010.
4. T. Nakano and M. Goto, "VocaListener: A singing-to-singing synthesissystem based on iterative parameter estimation, " Proc. SMC2009, pp. 343-348, July 2009.
5. T. Nakano and M. Goto, "Vocalistener2: A singing synthesissystem able to mimic a user's singing in terms of voice timbrechanges as well as pitch and dynamics, " Proc. ICASSP, pp. 453-456, May 2011.
6. F. Villavicencio and J. Bonada, "Applying voice conversion toconcatenative singing-voice synthesis, " Proc. INTERSPEECH, pp. 2162-2165, Sept. 2010.
7. Y. Kawakami, H. Banno, and F. Itakura, "GMM voice conversionof singing voice using vocal tract area function, " IEICE technicalreport. Speech (Japanese edition), vol. 110, no. 297, pp. 71-76, Nov. 2010.
8. Y. Stylianou, O. Cappé, and E. Moulines, "Continuous probabilistictransform for voice conversion, " IEEE Trans. SAP, vol. 6, no. 2, pp. 131-142, Mar. 1998.
9. T. Toda, A. W. Black, and K. Tokuda, "Voice conversion based onmaximum likelihood estimation of spectral parameter trajectory, "IEEE Trans. ASLP, vol. 15, no. 8, pp. 2222-2235, Nov. 2007.
10. T. Toda, Y. Ohtani, and K. Shikano, "One-to-many and many-toonevoice conversion based on eigenvoices, " Proc. ICASSP, pp. 1249-1252, Apr. 2007.
11. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, "Many-tomanyeigenvoice conversion with reference voice, " Proc. INTERSPEECH, pp. 1623-1626, Sept. 2009.
12. H. Doi, T. Toda, T. Nakano, M. Goto, and S. Nakamura, "Singingvoice conversion method based on many-to-many eigenvoice conversionand training data generation using a singing-to-singingsynthesis system, " Proc. APSIPA ASC, Nov. 2012.
13. K. Kobayashi, T. Toda, G. Neubig, S. Sakti, and S. Nakamura, "Statistical singing voice conversion with direct waveform modificationbased on the spectrum differential, " Proc. INTERSPEECH, pp. 2514-2418, Sept. 2014.
14. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-basedspeech synthesis, " Proc. ICASSP, pp. 1315-1318, June 2000.
15. M. Sambur, "Selection of acoustic features for speaker identification, "IEEE Trans. ASSP, vol. 23, no. 2, pp. 176-182, 1975.
16. H. Kawahara, I. Masuda-Katsuse, and A. Cheveigné, "Restructuringspeech representations using a pitch-adaptive time-frequencysmoothing 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, Apr. 1999.
17. S. Imai, K. Sumita, and C. Furuichi, "Mel log spectrum approximation(mlsa) filter for speech synthesis, " Electronics and Communicationsin Japan (Part I: Communications), vol. 66, no. 2, pp. 10-18, 1983.
18. S. Takamichi, T. Toda, A. Black, and S. Nakamura, "Modulationspectrum-based post-filter for gmm-based voice conversion, " APSIPAASC, Dec. 2014.