Speech Synthesis (SynSig)

Click here to visit the SIG website!

Aims. The SYNSIG Special Interest Group was formed to promote activities related to furthering the science of speech synthesis. The SIG brings together colleagues with a special interest in Speech Synthesis. It promotes interest in speech synthesis including text-to-speech conversion, concept-to-speech conversion and related disciplines, provides a means of exchanging news on recent developments in research and applications through a web site and the organisation of meetings, workshops and other activities (for instance evaluation), and makes available relevant resources for education.

Motivation.  At an international conference on speech processing, a speech scientist once held up a tube of toothpaste (whose brand was "Signal") and, squeezing it in front of the audience, coined the phrase "This is speech synthesis; speech recognition is the art of pushing the toothpaste back into the tube." One could turn this very simplistic view the other way round: users are generally much more tolerant of speech recognition errors than they are willing to listen to unnatural speech. There is magic in a speech recognizer that transcribes continuous radio speech into text with a word accuracy as low as 50%; in contrast, even a perfectly intelligible speech synthesizer is only moderately tolerated by users if it delivers nothing more than "robot voices". Delivering both intelligibility and naturalness has been the holy grail of speech synthesis research for the past 30 years. More recently, expressivity has been added as a major objective of speech synthesis. Add to this the engineering costs (computational cost, memory cost, design cost for making another synthetic voice or another language) which have to be taken into account, and you'll start to have an idea of the challenges underlying text-to-speech synthesis.

Board

• Chairperson: Esther Klabbers (ReadSpeaker, USA)
• Secretary : Gustav Eje Henter (KTH, Sweden)
• ISCA liaison officer : Zhenhua Ling (USTC, USA)

ISCA-supported events

1. Speech synthesis workshops:
   • SSW 2019, 20/9-22/9, Vienna, Austria
   • SSW 2016, 13/9-15/9, San Franscico, CA, USA
   • SSW 2013, 31/8-2/9, Barcelona, Spain.
   • SSW 2010, 22/9-24/9, Kyoto, Japan
   • SSW 2007, 22/8-24/8, Bonn, Germany
   • SSW 2004, 14/6-16/6, Pittsburgh, PA, USA
   • SSW 2001, 29/8-1/9, Pitlochry, Perthshire, Scotlan.
   • SSW 1998 (Dedicated to the memory of Christian Benoît), 26/11-29/11, Jenolan Caves House, Blue Mountains, Australia.
   • SSW 1994, 12/9-15/9, Mohonk Mountain House, New Paltz, NY, USA.
   • SSW 1990, 25/9-28/9, Autrans, France.
2. Blizzard challenges: since 2005, a speech synthesis challenge is organized every year:
   • Blizzard Challenge 2019, 23/9, Vienna, Austria (in conjunction with Interspeech & SSW)
   • Blizzard Challenge 2015, 11/9, Dresden, Germany(in conjunction with Interspeech)
   • Blizzard Challenge 2014, 19/9, Singapour (in conjunction with Interspeech)
   • Blizzard Challenge 2013, 2/9, Barcelona, Spain (in conjunction with SSW8)
   • Blizzard Challenge 2012, 14/9, Portland, OR (in conjunction with Interspeech)
   • Blizzard Challenge 2011, 2/9, Turin, Italy (in conjunction with Interspeech)
   • Blizzard Challenge 2010, 25/9, Kansai Science City, Japan (in conjunction with SSW7)
   • Blizzard Challenge 2009, 4/9, University of Edinburgh
   • Blizzard Challenge 2008, Brisbane, Australia (in conjunction with Interspeech)
   • Blizzard Challenge 2007, 25/8, Bonn, Germany (in conjunction with SSW5)
   • Blizzard Challenge 2006, 16/9, Pittsburgh, PA (in conjunction with Interspeech)
   • Blizzard Challenge 2005, 9/9, Lisboa, Portugal (in conjunction with Interspeech/Eurospeech)
3. Voice Conversion challenges:
   • Voice Conversion Challenge 2018
   • Voice Conversion Challenge 2016

Join the SIG - Discussion list