BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modulation spectrum-based approach to high-quality statistical par
 ametric speech synthesis  - Shinnosuke Takamichi (NAIST\, Japan)
DTSTART:20141117T120000Z
DTEND:20141117T130000Z
UID:TALK55914@talks.cam.ac.uk
CONTACT:Rogier van Dalen
DESCRIPTION:This talk presents Modulation Spectrum (MS)-based approach to 
 high-quality statistical parametric speech synthesis including text-to-spe
 ech synthesis and voice conversion. Many attempts\, such as Hidden Markov 
 Model (HMM)-based speech synthesis and Gaussian Mixture Model (GMM)-based 
 voice conversion\, are studied to produce various voices of the world. One
  of the critical problem of the statistical parametric speech synthesis is
  the excessive quality degradation of the synthetic speech. This is becaus
 e the detailed characteristics of the speech parameters are overly smoothe
 d by the statistical processing. This talk introduces the MS to alleviate 
 the quality degradation. The MS has better capability to sensitively captu
 re the over-smoothing effect than the conventional measures\, such as mel-
 cepstral distortion and global variance. I integrate the MS into the train
 ing or synthesis phase of HMM-based speech synthesis and GMM-based voice c
 onversion. The result of the perceptual test demonstrates the significant 
 improvements in synthetic speech quality.\n\nShinnosuke Takamichi is a Ph.
 D student with Tomoki Toda at Nara Institute of Science and Technology (Ja
 pan). Additionally\, he is a visiting researcher at Carnegie Mellon Univer
 sity (US).\n\nSandwiches will be provided.
LOCATION:Department of Engineering - Oatley 1 Meeting Room
END:VEVENT
END:VCALENDAR