Alleviating the over-smoothing problem in GMM-based voice conversion with discriminative training

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

Volumn , Issue , 2013, Pages 3062-3066

  Hwang, Hsin Te ^a,c   Tsao, Yu ^b   Wang, Hsin Min ^c   Wang, Yih Ru ^a   Chen, Sin Horng ^a  

^a NATIONAL CHIAO TUNG UNIVERSITY   (Taiwan)

^b RESEARCH CENTER FOR INFORMATION TECHNOLOGY INNOVATION   (Taiwan)

^c INSTITUTE OF INFORMATION SCIENCE   (Taiwan)

Author keywords

Discriminative training; GMM; Voice conversion

Indexed keywords

ACOUSTIC WAVE EFFECTS;

DISCRIMINATIVE POWER; DISCRIMINATIVE TRAINING; GAUSSIAN MIXTURE MODEL; GMM; JOINT DENSITIES; OBJECTIVE EVALUATION; SUBJECTIVE EVALUATIONS; VOICE CONVERSION;

SPEECH PROCESSING;

EID: 84906281888     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Y. Stylianou, O. Cappé, and E. Moulines, "Continuous probabilistic transform for voice conversion, " IEEE Trans. Speech Audio Process., vol. 6, no. 2, pp.131-142, Mar. 1998.
2. A. Kain, and M. W. Macon, "Spectral voice conversion for textto-speech synthesis, " Proc. ICASSP, 1998, vol. 1, pp. 285-288.
3. T. Toda, A.W. Black, and K. Tokuda, "Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory, " IEEE Trans. Audio, Speech, Lang., Process., vol. 15, no. 8, pp. 2222-2235, Nov. 2007.
4. D. Erro, A. Moreno, and A. Bonafonte, "Voice conversion based on weighted frequency warping, " IEEE Trans. Audio, Speech, Lang., Process., vol. 18, no. 5, pp. 922-931, July. 2010.
5. E. Godoy, O. Rosec, and T. Chonavel, "Voice conversion using dynamic frequency warping with amplitude scaling, for parallel or nonparallel corpora, " IEEE Trans. Audio, Speech, Lang., Process, vol. 20, no. 4, pp. 1313-1323, May. 2012.
6. H. T. Hwang, Y. Tsao, H. M. Wang, Y. R. Wang and S. H. Chen, "A study of mutual information for GMM-based spectral conversion, " Proc. INTERSPEECH, 2012.
7. H. T. Hwang, Y. Tsao, H. M. Wang, Y. R. Wang and S. H. Chen, "Exploring mutual information for GMM-based spectral conversion, " Proc. ISCSLP, 2012, pp. 50-54.
8. H. Benisty and D. Malah, "Voice conversion using GMM with enhanced global variance", Proc. INTERSPEECH, 2011, pp. 669-672.
9. H. Zen, Y. Nankaku, and K. Tokuda, "Continuous stochastic feature mapping based on trajectory HMMs, " IEEE Trans. Audio, Speech, Lang., Process., vol. 19, no. 2, pp. 417-430, Feb. 2011.
10. D. Saito, S. Watanabe, A. Nakamura, and N. Minematsu, "Statistical voice conversion based on noisy channel model, " IEEE Trans. Audio, Speech, Lang., Process., vol. 20, no. 6, pp. 1784-1794, Aug. 2012.
11. A. Mouchtaris, Y. Agiomyrgiannakis, and Y. Stylianou, "Conditional vector quantization for voice conversion, " Proc. ICASSP, 2007, vol. 4, pp. 505-508.
12. E. Godoy, O. Rosec, and T. Chonavel, "Alleviating the one-tomany mapping problem in voice conversion with contextdependent modeling", Proc. INTERSPEECH, 2009, pp. 1627-1630.
13. L. R. Bahl, P.F. Brown, P. V. De Souza, and L. R., Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition, " Proc. ICASSP, 1986, vol. 11, pp. 49-52.
14. B. H. Juang, W. Chou, and C. H. Lee, "Minimum classification error rate methods for speech recognition, " IEEE Trans. Speech Audio Process., vol. 5, no. 3, pp. 257-265, May. 1997.
15. 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 Commun., vol. 27, no. 3-4, pp.187-207, 1999.