Modulation spectrum-based post-filter for GMM-based Voice Conversion

2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014

Volumn , Issue , 2014, Pages

  Takamichi, Shinnosuke ^a,b   Toda, Tomoki ^a   Black, Alan W ^b   Nakamura, Satoshi ^a  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^b Carnegie Mellon University ^*  (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; MARKOV PROCESSES; SPEECH PROCESSING; TRELLIS CODES;

CONVERSION PROCESS; EXPERIMENTAL EVALUATION; GAUSSIAN MIXTURE MODEL; MODULATION SPECTRUM; QUALITY DEGRADATION; SPEECH-BASED SYSTEMS; STATISTICAL APPROACH; STATISTICAL MODELING;

MODULATION;

EID: 84949926049     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/APSIPA.2014.7041540     Document Type: Conference Paper

References (18)

1. K. Tanaka, T. Toda, G. Neubig, S. Sakti, and S. Nakamura. An evaluation of excitation feature prediction in a hybrid approach to electrolaryngeal speech enhancement. In Proc. ICASSP, pp. 4521-4525, Florence, Italy, May 2014.
2. K. Kobayashi, T. Toda, T. Nakano, M. Goto, G. Neubig, S. Sakti, and S. Nakamura. Regression approaches to perceptual age control in singing voice conversion. In Proc. ICASSP, pp. 7954-7958, Florence, Italy, May 2014.
3. N. Hattori, T. Toda, H. Kawai, H. Saruwatari, and K. Shikano. Speakeradaptive speech synthesis based on eigenvoice conversion and languagedependent prosodic conversion in speech-to-speech translation. In Proc. INTERSPEECH, pp. 2769-2772, Florence, Italy, Aug. 2011.
4. S. Aryal and R. G.-Osuna. Can voice conversion be used to reduce non-native accents? In Proc. ICASSP, pp. 7929-7933, Florence, Italy, May 2014.
5. T. Toda, A. W. Black, and K. Tokuda. Voice conversion based on maximum likelihood estimation of spectral parameter trajectory. IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 8, pp. 2222-2235, 2007.
6. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura. Incorporation of mixed excitation model and postfilter into HMM-based text-to-speech synthesis. IEICE Trans. Inf. Syst., Vol. J87-D-II, No. 8, pp. 1563-1571, 2004.
7. F. Eyben and Y. Agiomyrgiannakis. A frequency-weighted post-filtering transform for compensation of the over-smoothing effect in HMM-based speech synthesis. In Proc. ICASSP, pp. 275-279, Florence, Italy, May 2014.
8. T. Toda, T. Muramatsu, and H. Banno. Implementation of conputationally efficient real-time voice conversion. In Proc. INTERSPEECH, Portland, Oregon, U. S., Sept. 2012.
9. Y. Jiao, X. Na, and M. Tu. Improving voice quality of HMM-based speech synthesis using voice conversion method. In Proc. ICASSP, pp. 7964-7968, Florence, Italy, May 2014.
10. H. Hwang, Y. Tsao, H. Wang, Y. Wang, and S. Chen. Incorporating global variance in the training phase of GMM-based voice conversion. In Proc. APSIPA, pp. 1-6, Kaohsiung, Taiwan, Oct. 2013.
11. R. Drullman, J. M. Festen, and R. Plomp. Effect of reducing slow temporal modulations on speech reception. J. Acoust. Soc. of America, Vol. 95, pp. 2670-2680, 1994.
12. S. Thomas, S. Ganapathy, and H. Hermansky. Phoneme recgnition usng spectral envelop and modulation frequency features. In Proc. ICASSP, pp. 4453-4456, Taipei, Taiwan, April 2009.
13. S. Takamichi, T. Toda, G. Neubig, S. Sakti, and S. Nakamura. A postfilter to modify modulation spectrum in HMM-based speech synthesis. In Proc. ICASSP, pp. 290-294, Florence, Italy, May 2014.
14. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura. Speech parameter generation algorithms for HMM-based speech synthesis. In Proc. ICASSP, pp. 1315-1318, Istanbul, Turkey, June 2000.
15. Y. Sagisaka, K. Takeda, M. Abe, S. Katagiri, T. Umeda, and H. Kuawhara. A large-scale Japanese speech database. In ICSLP90, pp. 1089-1092, Kobe, Japan, Nov. 1990.
16. H. Kawahara, Jo Estill, and O. Fujimura. Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT . In MAVEBA 2001, pp. 1-6, Firentze, Italy, Sept. 2001.
17. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano. Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation. In Proc. INTERSPEECH, pp. 2266-2269, Pittsburgh, U. S. A., Sep. 2006.
18. H. Kawahara, I. Masuda-Katsuse, and A. D. Cheveigne. 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.