Speech sample (MS param. gen.)

Speech samples in HMM-based TTS

GV ... speech parameter generation w/ Global Variance (GV) [Toda et al., 2007.]

MS ... speech parameter generation w/ Modulation Spectrum (MS) [Our proposed method]

Speaker ... RMS from ARCTIC speech database [Kominek et al., 2003.]

Our setting ... see our paper.

References

[Toda et al., 2007.] T. Toda and K. Tokuda, “A speech parameter generation algorithm considering global variance for HMM-based speech synthesis,” IEICE Transactions on Information and Systems, vol. E90-D, no. 5, pp. 816-824, 2007.

[Kominek et al., 2003.] J. Kominek and A. W. Black, “The CMU ARCTIC speech databases for speech synthesis research,” in Tech. Rep. CMU-LTI-03-177, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, U.S.A., 2003.