Speech Synthesis Workshop (SSW)

From SynSIG
<div class="mw-revision"><div id="mw-revision-info">Revision as of 11:42, 4 July 2016 by <a href="/index.php?title=User:Peter.cahill&amp;action=edit&amp;redlink=1" class="new mw-userlink" title="User:Peter.cahill (page does not exist)"><bdi>Peter.cahill</bdi></a> <span class="mw-usertoollinks">(<a href="/index.php?title=User_talk:Peter.cahill&amp;action=edit&amp;redlink=1" class="new mw-usertoollinks-talk" title="User talk:Peter.cahill (page does not exist)">talk</a> | <a href="/index.php/Special:Contributions/Peter.cahill" class="mw-usertoollinks-contribs" title="Special:Contributions/Peter.cahill">contribs</a>)</span></div><div id="mw-revision-nav">(<a href="/index.php?title=Speech_Synthesis_Workshop_(SSW)&amp;diff=prev&amp;oldid=2549" title="Speech Synthesis Workshop (SSW)">diff</a>) <a href="/index.php?title=Speech_Synthesis_Workshop_(SSW)&amp;direction=prev&amp;oldid=2549" title="Speech Synthesis Workshop (SSW)">← Older revision</a> | <a href="/index.php/Speech_Synthesis_Workshop_(SSW)" title="Speech Synthesis Workshop (SSW)">Latest revision</a> (<a href="/index.php?title=Speech_Synthesis_Workshop_(SSW)&amp;diff=cur&amp;oldid=2549" title="Speech Synthesis Workshop (SSW)">diff</a>) | <a href="/index.php?title=Speech_Synthesis_Workshop_(SSW)&amp;direction=next&amp;oldid=2549" title="Speech Synthesis Workshop (SSW)">Newer revision →</a> (<a href="/index.php?title=Speech_Synthesis_Workshop_(SSW)&amp;diff=next&amp;oldid=2549" title="Speech Synthesis Workshop (SSW)">diff</a>)</div></div>

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.

Major challenges call for major meetings: the Speech Synthesis Workshops (SSWs), which are held every three years under the auspices of ISCA's SynSIG. SSWs provide a unique occasion for people in the speech synthesis area to meet each other. They contribute to establishing a feeling that we are all participating in a joint effort towards intelligible, natural, and expressive synthetic speech.

List of ISCA ITRW Speech Synthesis Workshops (SSW)

(Full papers are available on line)

  • SSW1, September 25-28, 1990, Autrans, France.
  • SSW2, September 12-15, 1994, Mohonk Mountain House, New Paltz, NY, USA.
  • SSW3 (Dedicated to the memory of Christian Benoît), November 26-29, 1998, Jenolan Caves House, Blue Mountains, Australia.
  • SSW4, August 29 - September 1, 2001, Atholl Palace Hotel, Pitlochry, Perthshire, Scotland.
  • SSW5, June 14-16, 2004, Pittsburgh, PA, USA.
  • SSW6, August 22-24, 2007, Bonn , Germany.
  • SSW7, September 22-24, 2010, Kyoto, Japan.
  • SSW8, August 31 - September 2, 2013, Barcelona, Spain.
  • SSW9, September 13-15, 2016, Sunnyvale, California, USA.

SynSIG is a Special Interest Group of ISCA, the International Speech Communication Association.

SynSIG 1998-2024