Vocal tract length normalization for statistical parametric speech synthesis

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 7, 2012, Pages 2134-2148

  Saheer, Lakshmi ^a,b   Dines, John ^a   Garner, Philip N ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b EPFL   (Switzerland)

Author keywords

Expectation maximization optimization; hidden Markov model (HMM) based statistical parametric speech synthesis; speaker adaptation; vocal tract length normalization

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; EFFICIENT IMPLEMENTATION; EXPECTATION MAXIMIZATION; JACOBIANS; RAPID SPEAKER ADAPTATION; SPEAKER ADAPTATION; TRANSFORMATION MATRICES; VOCAL TRACT LENGTH NORMALIZATION; WARPING FACTORS;

HIDDEN MARKOV MODELS; LINEAR TRANSFORMATIONS; MAXIMUM PRINCIPLE; SPEECH RECOGNITION;

SPEECH SYNTHESIS;

EID: 84862291337     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2198058     Document Type: Article

References (29)

1. A. W. Black, H. Zen, and K. Tokuda, "Statistical parametric speech synthesis," in Proc. ICASSP, 2007, pp. 1229-1232.
2. J. Yamagishi, T. Kobayashi, Y. Nakano, K. Ogata, and J. Isogai, "Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 1, pp. 66-83, Jan. 2009.
3. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., vol. 12, no. 2, pp. 75-98, 1998. (Pubitemid 128383747)
4. L. Lee and R. Rose, "A frequency warping approach to speaker normalization," IEEE Trans. Speech Audio Process., vol. 6, no. 1, pp. 49-60, Jan. 1998. (Pubitemid 128720631)
5. L. Saheer, P. N. Garner, J. Dines, and H. Liang, "VTLN adaptation for statistical speech synthesis," in Proc. ICASSP, Mar. 2010, pp. 4838-4841.
6. L. Saheer, J. Dines, P. N. Garner, and H. Liang, "Implementation of VTLN for statistical speech synthesis," in Proc. 7th ISCA Speech Synth. Workshop, Kyoto, Japan, Sep. 2010, pp. 224-229.
7. L. Saheer, P. N. Garner, and J. Dines, "Study of Jacobian normalization for VTLN," Idiap-RR-25-2010, 2010.
8. M. Pitz, "Investigations on linear transformations for speaker adaptation and normalization," Ph.D. dissertations, RWTH Aachen Univ., Aachen, Germany, 2005.
9. S. Umesh, A. Zolnay, and H. Ney, "Implementing frequency warping and VTLN through linear transformation of conventional MFCC," in Proc. Interspeech, Lisbon, Portugal, 2005, pp. 269-271.
10. S. Panchapagesan and A. Alwan, "Frequency warping for VTLN and speaker adaptation by linear transformation of standard MFCC," Comput. Speech Lang., vol. 23, no. 1, pp. 42-64, 2009.
11. M. Pitz and H. Ney, "Vocal tract normalization equals linear transformation in cepstral space," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 930-944, Sep. 2005. (Pubitemid 41558907)
12. J. W. McDonough, "speaker compensation with all-pass transforms," Ph.D. dissertations, John Hopkins Univ., Baltimore, MD, 2000.
13. L. F. Uebel and P. C. Woodland, "An investigation into vocal tract length normalisation," in Proc. Eur. Conf. Speech Commun. Technol., 1999, pp. 2527-2530.
14. D. Sündermann, "Text-independent voice conversion," Ph.D. dissertation, Bundeswehr Univ. Munich, Munich, Germany, 2008.
15. K. Tokuda, T. Kobayashi, T. Masuko, and S. Imai, "Mel-generalized cepstral analysis-A unified approach to speech spectral estimation," in Proc. ICSLP, Sep. 1994, vol. 3, pp. 1043-1046.
16. M. Hirohata, T. Masuko, and T. Kobayashi, "A study on average voice model training using vocal tract length normalization," (in Japanese) IEICE Tech. Rep., vol. 103, no. 27, pp. 69-74, 2003.
17. P. T. Akhil, S. P. Rath, S. Umesh, and D. R. Sanand, "A computationally efficient approach to warp factor estimation in VTLN using EM algorithm and sufficient statistics," in Proc. Interspeech, Brisbane, Australia, 2008, pp. 1713-1716.
18. D. Oppenheim and A. V. Johnson, "Discrete representation of signals," Proc. IEEE, vol. 60, no. 6, pp. 681-691, Jun. 1972.
19. A. Sankar and C.-H. Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Process., vol. 4, no. 3, pp. 190-202, May 1996. (Pubitemid 126753005)
20. T. Emori and K. Shinoda, "Rapid vocal tract length normalization using maximum likelihood estimation," in Proc. Eurospeech, 2001, pp. 1649-1652.
21. W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C. Cambridge, U.K.: Cambridge Univ. Press, 1992.
22. S. P. Rath and S. Umesh, "Acoustic class specific VTLN-warping using regression class trees," in Proc. Interspeech, Brighton, U.K., 2009, pp. 556-559.
23. S. Molau, S. Kanthak, and H. Ney, "Efficient vocal tract normalization in ASR," in Proc. ESSV, Cottbus, Germany, 2000.
24. A. Miguel, E. Lleida, R. L. Buera, and A. Ortega, "Augemented state space acoustic decoding for modeling local variability in speech," in Proc. Interspeech, Lisbon, Portugal, 2005.
25. J. Yamagishi, T.Nose, H. Zen, Z.-H. Ling,T. Toda, K. Tokuda, S. King, and S. Renals, "Robust speaker-adaptive HMM-based text-to-speech synthesis," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 6, pp. 1208-1230, Aug. 2009.
26. G. Garau, "Speaker normalization for large vocabulary multiparty conversational speech recognition," Ph.D. dissertation, Univ. of Edinburgh, Edinburgh, U.K., 2008.
27. D.R. Sanand, S.P.Rath, andS. Umesh,"A studyon the influenceof co-variance adaptation on Jacobian compensation in vocal tract length normalization," in Proc. Interspeech, Brighton, U.K., 2009, pp. 584-587.
28. A. Faria and D. Gelbart, "Efficient pitch-based estimation of VTLN warp factors," in Proc. Interspeech, Sep. 2005, pp. 213-216. (Pubitemid 43908039)
29. J. Yamagishi, O. Watts, S. King, and B. Usabaev, "Roles of the average voice in speaker-adaptive HMM-based speech synthesis," in Proc. In-terspeech, Sep. 2010, pp. 418-421.