W3C to Expand Internationalization in Speech Synthesis Markup Language

Goal is to increase support of world's languages in voice applications

 

http://www.w3.org/ -- 3 August 2006 -- Today, the W3C announced the results of the second Workshop on Speech Synthesis Markup Language, where speech experts from around the world presented ideas for expanding the range of languages supported by SSML 1.0.

The results include a new initiative to revise SSML 1.0 in ways that support a wider range of the world's languages, including the widely spoken languages of Mandarin, Hindi, Arabic, Russian, Hebrew, and other languages spoken in India and Asia.

These results reinforce important discoveries reached at the first SSML Workshop in Beijing late last year, which provided critical information on many Asian languages.

The announcement of the second workshop results serves as a call for participation to researchers around the world to join the effort to improve the specification.

Voice Applications and Under-represented Languages Are Growing on the Web

It is estimated that within three years, the World Wide Web will contain significantly more content from currently under-represented languages, such as Chinese and Indian language families.

In many of the regions where these languages are spoken, people can access the Web more easily through a mobile handset than through a desktop computer. There are more than 10 times as many cellphones in the world today as there are Internet-connected PCs.

An improved SSML will increase the ability of people world-wide to listen to synthesized speech through mobile phones, desktop computers, or other devices, greatly extending the reach of computation and information delivery into nearly every corner of the globe.

Expanding the Range of Languages Supported in Standards is Critical

The participants in the W3C Workshop reached conclusions that support the expansion of the SSML standard.

For example, the Workshop participants expressed the need to add to the standard the ability to represent features of spoken language, including tone, syllabic stress or accent, and duration in a machine-readable fashion. In some languages, these attributes are an important factor in determining meaning.

The goal of the next phase is to identify a few basic mechanisms that can greatly extend the power of SSML to better cover more of the world's languages.

W3C Invites Current and New Members to Join Efforts

W3C is moving forward on enhancing and expanding the capabilities of SSML, based on the results of the Workshop. Organizations, particularly those with native understanding of the languages of Japan, China, Korea, Russia and India are encouraged to join W3C and participate in the W3C Voice Browser Activity.

About the World Wide Web Consortium [W3C]

The World Wide Web Consortium (W3C) is an international consortium where Member organizations, a full-time staff, and the public work together to develop Web standards. W3C primarily pursues its mission through the creation of Web standards and guidelines designed to ensure long-term growth for the Web. Over 400 organizations are Members of the Consortium. W3C is jointly run by the MIT Computer Science and Artificial Intelligence Laboratory (MIT CSAIL) in the USA, the European Research Consortium for Informatics and Mathematics (ERCIM) headquartered in France and Keio University in Japan,and has additional Offices worldwide. For more information see http://www.w3.org/

 

Contact Americas, Australia --

Janet Daly, <janet@w3.org>, +1.617.253.5884 or +1.617.253.2613

Contact Europe, Africa and the Middle East --

Marie-Claire Forgue, <mcf@w3.org>, +33.492.38.75.94

Contact Asia --

Yasuyuki Hirakawa <chibao@w3.org>, +81.466.49.1170