Modulation spectrum-constrained trajectory training algorithm for HMM-based speech synthesis

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

Volumn 2015-January, Issue , 2015, Pages 1206-1210

  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

Global variance; HMM based speech synthesis; Modulation spectrum; Over smoothing; Trajectory training

Indexed keywords

ALGORITHMS; GAUSSIAN DISTRIBUTION; HIDDEN MARKOV MODELS; MARKOV PROCESSES; MODULATION; PARAMETER ESTIMATION; SPEECH; SPEECH COMMUNICATION; SPEECH SYNTHESIS; TRAJECTORIES; TRELLIS CODES;

COMPUTATIONALLY EFFICIENT; CONSTRAINED TRAJECTORIES; CONVENTIONAL GENERATION; GAUSSIAN MIXTURE MODEL; GLOBAL VARIANCE; HMM-BASED SPEECH SYNTHESIS; MODULATION SPECTRUM; OVER-SMOOTHING;

PLASMA DIAGNOSTICS;

EID: 84959166270     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (32)

1. K. Tokuda, Y. Nankaku, T. Toda, H. Zen, J. Yamagishi, and K. Oura, "Speech synthesis based on hidden Markov models, "Proceedings of the IEEE, vol. 101, no. 5, pp. 1234-1252, 2013.
2. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and durationin HMM-based speech synthesis, " in Proc. EUROSPEECH, Budapest, Hungary, Apr. 1999, pp. 2347-2350.
3. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-basedspeech synthesis, " in Proc. ICASSP, Istanbul, Turkey, June 2000, pp. 1315-1318.
4. T. Yoshimura, T. Masuko, K. Tokuda, T. Kobayashi, and T. Kitamura, "Speaker interpolation for HMM-based speech synthesissystem, " J. Acoust. Soc. Jpn. (E), vol. 21, no. 4, pp. 199-206, 2000.
5. J. Yamagishi and T. Kobayashi., "Average-voice-based speechsynthesis using HSMM-based speaker adaptation and adaptivetraining, " IEICE Trans., Inf. and Syst., vol. E90-D, no. 2, pp. 533-543, 2007.
6. T. Nose, J. Yamagishi, T. Masuko, and T. Kobayashi, "A stylecontrol technique for HMM-based expressive speech synthesis, "IEICE Trans., Inf. and Syst., vol. E90-D, no. 9, pp. 1406-1413, 2007.
7. K. Shirota, K. Nakamura, K. Hashimoto, K. Oura, Y. Nankaku, and K. Tokuda, "Integration of speaker and pitch adaptive trainingfor HMM-based singing voice synthesis, " in Proc. ICASSP, Florence, Italy, May 2014, pp. 2578-2582.
8. J. Yamagishi, C. Veaux, S. King, and S. Renals, "Speech synthesistechnologies for individuals with vocal diabilities: Voice bankingand reconstruction, " Acoust. Sci. technol., vol. 33, pp. 1-5, 2012.
9. Y. Sagisaka, "Speech synthesis by rule using an optimal selectionof non-uniform synthesis units, " in Proc. ICASSP, New York, U. S. A., Apr. 1988, pp. 679-682.
10. H. Zen and A. Senior, "Deep mixture density networks for acousticmodeling in statistical parametric speech synthesis, " in Proc. ICASSP, Florence, Italy, May 2014, pp. 3872-3876.
11. T. Kano, S. Takamichi, S. Sakti, T. T. G. Neubig, and S. Nakamura, "Generalizing continuous-space translation of paralinguisticinformation, " in Proc. INTERSPEECH, Lyon, France, Aug2013, pp. 2614-2618.
12. S. King and V. Karaiskos, "The blizzard challenge 2011, " in Proc. Blizzard Challenge workshop, Turin, Italy, Sept. 2011.
13. S. Takamichi, T. Toda, G. Neubig, S. Sakti, and S. Nakamura, "Apostfilter to modify modulation spectrum in HMM-based speechsynthesis, " in Proc. ICASSP, Florence, Italy, May 2014, pp. 290-294.
14. S. Takamichi, T. Toda, A. W. Black, and S. Nakamura, "Modulationspectrum-based post-filter for GMM-based voice conversion, "in Proc. APSIPA ASC, Siem Reap, Cambodia, Dec. 2014.
15. -, "Modified modulation spectrum-based post-filter forHMM-based speech synthesis, " in Proc. GlobalSIP, Atlanta, United States, Dec. 2014, pp. 710-714.
16. T. Toda and K. Tokuda, "A speech parameter generation algorithmconsidering global variance for HMM-based speech synthesis, "IEICE Trans., vol. E90-D, no. 5, pp. 816-824, 2007.
17. S. Takamichi, T. Toda, A. W. Black, and S. Nakamura, "Parametergeneration algorithm considering modulation spectrum for HMMbasedspeech synthesis, " in Proc. ICASSP, Brisbane, Australia, Apr. 2015.
18. T. Nose and A. Ito, "Analysis of spectral enhancement usingglobal variance in HMM-based speech synthesis, " in Proc. INTERSPEECH, MAXAtria, Singapore, May 2014, pp. 2917-2921.
19. H. Hwang, Y. Tsao, H. Wang, Y. Wang, and S. Chen, "Incorporatingglobal variance in the training phase of GMM-based voiceconversion, " in Proc. APSIPA, Kaohsiung, Taiwan, Oct. 2013, pp. 1-6.
20. M. Shannon and W. Byrne, "Fast, low-artifact speech synthesisconsidering global variance, " in Proc. ICASSP, Vancouver, Canada, May. 2013, pp. 7869-7873.
21. T. Toda and S. Young, "Trajectory training considering globalvariance for HMM-based speech synthesis, " in Proc. ICASSP, Taipei, Taiwan, Aug. 2009, pp. 4025-4028.
22. H. Zen, K. Tokuda, and T. Kitamura, "Refomulating the HMMas a trajectory model by imposing explicit relationships betweenstatic and dynamic feature vector sequences, " Computer Speechand Language, vol. 21, no. 1, pp. 153-173, Jan. 2007.
23. S. Takamichi, T. Toda, A. W. Black, and S. Nakamura, "Modulationspectrum-constrained trajectory training algorithm for GMMbasedvoice conversion, " in Proc. ICASSP, Brisbane, Australia, Apr. 2015.
24. T. Toda, A. W. Black, and K. Tokuda, "Voice conversion based onmaximum likelihood estimation of spectral parameter trajectory, "IEEE Transactions on Audio, Speech and Language Processing, vol. 15, no. 8, pp. 2222-2235, 2007.
25. K. Tokuda, T. Masuko, B. Miyazaki, and T. Kobayashi, "Multispaceprobability distribution HMM, " IEICE Trans., Inf. and Syst., vol. E85-D, no. 3, pp. 455-464, 2002.
26. K. Yu and S. Young, "Continuous F0 modeling for HMMbased statistical parametric speech synthesis, " IEEE Trans. Audio, Speech and Language, vol. 19, no. 5, pp. 1071-1079, 2011.
27. H. Zen, K. Tokuda, T. K. T. Masuko, and T. Kitamura, "Hiddensemi-Markov model based speech synthesis system, " IEICETrans., Inf. and Syst., E90-D, no. 5, pp. 825-834, 2007.
28. J. Kominek and A. W. Black, "The CMU ARCTIC speechdatabases for speech synthesis research, " in Tech. Rep. CMU-LTI-03-177, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, U. S. A., 2003.
29. H. Kawahara, J. Estill, and O. Fujimura, "Aperiodicity extractionand control using mixed mode excitation and group delay manipulationfor a high quality speech analysis, modification and synthesissystem STRAIGHT, " in MAVEBA 2001, Firentze, Italy, Sept. 2001, pp. 1-6.
30. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, "Maximumlikelihood voice conversion based on GMM with STRAIGHTmixed excitation, " in Proc. INTERSPEECH, Pittsburgh, U. S. A., Sep. 2006, pp. 2266-2269.
31. H. Kawahara, I. Masuda-Katsuse, and A. D. Cheveigne, "Restructuringspeech representations using a pitch-adaptive timefrequencysmoothing and an instantaneous-frequency-based F0extraction: Possible role of a repetitive structure in sounds, "Speech Commun., vol. 27, no. 3-4, pp. 187-207, 1999.
32. S. Takamichi, T. Toda, Y. Shiga, S. Sakti, G. Neubig, and S. Nakamura, "Parameter generation methods with rich context modelsfor high-quality and flexible text-to-speech synthesis, " IEEE Journalof Selected Topics in Signal Processing, vol. 8, no. 2, pp. 239-250, 2014.