TWiki> CSTR Web>Speak08To09 (04 Feb 2010, Main.korin)EditAttach

-- 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


11.11.08 Discussion of the work of Javier Latorre on polyglot speech synthesis, led by Oliver. See latorre-2006 attached below. The paper mostly deals with porting a given speaker's voice characteristics to languages for which we have no data for that speaker (but have data for other speakers in that language). However, one part of the experiment reported in the article deals with synthesis of languages for which we have no data at all by using acoustic models of similar speech units in languages that have been trained on. This is what I want to focus on in the discussion, and in this connection, it might be worth taking a look at Tanja Schultz's earlier paper on similar methods in ASR. I've also attached Latorre's doctoral thesis, just in case anyone wants to take a look.
18.11.08 Progress reports: Sebastian
25.11.08 Tuomo Raitio (visiting from TKK Helsinki University of Technology) - will present his work on source modelling in HMM-based speech synthesis (* NOTE: ROOM 4.31 *)
02.12.08 Progress reports: Junichi
09.12.08 Interspeech (+Blizzard) paper discussions
16.12.08 Progress reports: Volker
Christmas break Christmas break
13.01.09 Progress reports: Matthew
26.01.09 Discussion of STRAIGHT (two papers STRAIGHT-original.pdf ("the" paper) and STRAIGHT-Implement.pdf (additional, shorter note on implementation))
02.02.09 Progress reports: Gregor
09.02.09 Interspeech (+Blizzard) paper discussions
16.02.09 Progress reports: Leonardo
23.02.09

  • ustc_Blizzard2008.pdf: Zhen-Hua Ling et al. "The USTC System for Blizzard Challenge 2008" in Proc. Blizzard Workshop 2008
  • IS061456.PDF: Paul Taylor, "Unifying Unit Selection and Hidden Markov Model Speech Synthesis". Proc Interspeech 2006
  • IS080193.PDF: Vincent Pollet, Andrew Breen. "Synthesis by Generation and Concatenation of Multiform Segments" in Proc. Interspeech 2008
02.03.09 Progress reports: Oliver
09.03.09
  • Zen survey paper (unpublished)
16.03.09 Progress reports: (no meeting)
23.03.09 Practice talks for Birmingham
30.03.09 Progress reports: (none - Birmingham meeting)
06.04.09 Presentation of Heiga Zen's survey work
13.04.09 Progress reports:
20.04.09
27.04.09 Progress reports:
04.05.09
11.05.09 Discussion about Interspeech synthesis demo
18.05.09 No meeting (University holiday)
25.05.09 Progress reports:
01.06.09 Progress reports: Korin
08.06.09 Junichi - EMIME Blizzard system
18.06.09 Maria - evaluating synthetic speech for older listeners ( NOTE unusual time slot)
22.06.09 Progress reports: Joao
29.06.09 Lit review cross-lingual voice similarity voice_similar_speak.pdf: Mirjam
06.07.09
13.07.09Discussion of Blizzard
20.07.09 Progress reports: Oliver
27.07.09
03.08.09
10.08.09 Progress reports: Volker
17.08.09 Progress reports: Matthew
24.08.09Ricardo Gutierrez-Osuna (visitor to CSTR)
31.08.09practice session for Interspeech "Voice Cloning" demo

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

  • IS090714.PDF: Interspeech paper on rich contexts for HMM TTS
Topic attachments
I Attachment Action Size Date Who Comment
pdfPDF IS061456.PDF manage 144.9 K 10 Feb 2009 - 15:18 SimonKing Paul Taylor, "Unifying Unit Selection and Hidden Markov Model Speech Synthesis". Proc Interspeech 2006
pdfPDF IS080193.PDF manage 448.7 K 10 Feb 2009 - 15:43 SimonKing Vincent Pollet, Andrew Breen. "Synthesis by Generation and Concatenation of Multiform Segments" in Proc. Interspeech 2008
pdfpdf IS090420.pdf manage 318.7 K 14 Sep 2009 - 10:43 Main.korin Shiga, Y. Interspeech2009 paper
pdfpdf IS090423.pdf manage 385.9 K 14 Sep 2009 - 11:05 Main.korin Chládková et al. Interspeech2009 paper (F0 affects F1)
pdfpdf IS090475.pdf manage 420.0 K 16 Nov 2009 - 22:56 Main.korin Drugman et al. complex cepstrum-based speech decomposition
pdfpdf IS090519.pdf manage 447.5 K 14 Sep 2009 - 10:33 Main.korin Drugman et al. Interspeech2009 paper
pdfPDF IS090714.PDF manage 812.7 K 27 Oct 2009 - 13:51 Main.korin Interspeech paper on rich contexts for HMM TTS
pdfpdf STRAIGHT-Implement.pdf manage 257.4 K 21 Jan 2009 - 15:46 Main.korin  
pdfpdf STRAIGHT-original.pdf manage 1318.3 K 21 Jan 2009 - 15:46 Main.korin  
pdfpdf brain-to-speech_bru_is09.pdf manage 504.2 K 15 Oct 2009 - 08:27 Main.s0679204  
pdfpdf javier_doctor.pdf manage 819.3 K 07 Oct 2008 - 16:45 Main.s0676515  
pdfpdf latorre-2006.pdf manage 235.1 K 07 Oct 2008 - 16:45 Main.s0676515  
pdfpdf new-cw_bellegarda_is09.pdf manage 640.8 K 15 Oct 2009 - 08:30 Main.s0679204  
pdfpdf schulz-2001.pdf manage 455.7 K 07 Oct 2008 - 16:46 Main.s0676515  
pdfpdf ustc_Blizzard2008.pdf manage 189.8 K 10 Feb 2009 - 15:45 SimonKing Zhen-Hua Ling et al. "The USTC System for Blizzard Challenge 2008" in Proc. Blizzard Workshop 2008
pdfpdf voice_similar_speak.pdf manage 118.9 K 01 Jul 2009 - 09:46 Main.mwester slides "voice similarity across languages"
Topic revision: r89 - 04 Feb 2010 - 15:21:34 - Main.korin
CSTR.Speak08To09 moved from CSTR.Speak on 04 Feb 2010 - 14:33 by Main.korin - put it back
 
This site is powered by the TWiki collaboration platformCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback
This Wiki uses Cookies