-- Main.korin - 02 Feb 2007

Speak! speech synthesis meeting.

The purpose of these regular informal meetings is to discuss and share progress relating to speech synthesis research within CSTR.

Anybody with an interest in speech synthesis (audio and visual) research is welcome.

* Meetings will typically be held in the Instrumented Meeting Room (IF Level3 W), but this may vary on odd occasions. The current time for meeting is Thursday at 4pm for an hour.

2008/2009 schedule

Suggested Papers from Interspeech 2009 conference:

• IS090519.pdf: Drugman et al. Interspeech2009 paper (Glottal source modelling for HMM TTS - Korin)

• IS090420.pdf: Shiga, Y. Interspeech2009 paper (Spectral representation for HMM TTS - Korin)

• IS090423.pdf: Chládková et al. Interspeech2009 paper (How F0 affects F1 - Korin)
• brain-to-speech_bru_is09.pdf: Brumberg et al. Interspeech (Brain-to-Speech - Junichi, Leonardo)
• new-cw_bellegarda_is09.pdf: Bellegarda Interspeech 2009 (Dynamic cost weighting in unit selection - Leonardo)
• Observation of empirical cumulative distribution of vowel spectral distances and its application to vowel based voice conversion, Kawahara et al (Simon)

• HMM-based Speaker Characteristics Emphasis Using Average Voice Model, Nose et al (Simon)
• IS090475.pdf: Drugman et al. complex cepstrum-based speech decomposition

other suggestions for meeting topics:

• Statistical Text-to-Speech Synthesis with Improved Dynamics. Stas Tiomkin, David Malah; Technion IIT, Israel. Proc Interspeech 2008

• Tomoki Toda's work on voice conversion using less than one sentence of speech

• The Expression and Perception of Emotions: Comparing Assessments of Self versus Others Carlos Busso, Shrikanth S. Narayanan; University of Southern California, USA. In Proc. Interspeech 2008

• Scripted Dialogs versus Improvisation: Lessons Learned About Emotional Elicitation Techniques from the IEMOCAP Database Carlos Busso, Shrikanth S. Narayanan; University of Southern California, USA. In Proc. Interspeech 2008

• ZZT transform (Dutoit's student thesis) - IEEE journal paper (ACTION ON Matthew to find this paper)

• Papers from ISCSLP 2008 (ACTION ON Junichi to look at this)

previously in Speak

• latorre-2006.pdf:

• javier_doctor.pdf:

• schulz-2001.pdf:

• STRAIGHT-original.pdf:

• STRAIGHT-Implement.pdf:

• voice_similar_speak.pdf: slides "voice similarity across languages"

• IS090714.PDF: Interspeech paper on rich contexts for HMM TTS