W3C Standard Simplifies Creation of Speech-Enabled Web Applications

Author(s) and publish date


Pronunciation Lexicon Specification Lowers Costs Through Reuse



http://www.w3.org/ -- 14 October 2008 -- W3C published today a standard that will simplify the development of Web applications that speak and listen to users. The Pronunciation Lexicon Specification (PLS) 1.0 is the newest piece of W3C's Speech Interface Framework for creating Web applications driven by voice and speech. PLS can reduce the cost of developing these applications by allowing people to share and reuse pronunciation dictionaries. In addition, PLS can make it easier to localize applications by separating pronunciation concerns from other parts of the application.

"Standard pronunciation lexicons were a missing piece in the W3C Speech Framework," said Paolo Baggia, Director of International Standards at Loquendo and editor of the PLS 1.0 specification. "I'm very happy to have actively contributed to filling this gap. As a result, starting today people can create '100% standard' voice applications."

Voice Interaction Part of W3C's One Web Vision

Real-world voice-driven Web applications abound, though people may not always realize they are interacting with a Web service; examples include airline departure and arrival information, banking transactions, automated phone appointment reminders, and automated telephone receptionists. By one estimate, over 85% of Interactive Voice Response (IVR) applications for telephones (including mobile) use W3C's VoiceXML 2.0 standard.

"There are 10 times as many phones in the world as connected PCs. Phones will become the major portal to the Web," said James A. Larson, co-Chair of the Voice Browser Working Group, which produced the new standard. "Speech recognition is not yet widely associated with the 'visual Web', but this will change as devices continue to shrink and make keyboards impractical, and as cell phones become more prevalent in regions with low literacy rates."

Asking for directions while driving and hearing the response through speech synthesis illustrates how practical "hands-free" applications can be to mobile users. Voice applications also benefit people with some disabilities (such as vision limitations) and people who cannot read.

W3C considers voice access to be one piece of more general "multimodal" access, where users can use combinations of means to interact: voice input, speech feedback, electronic ink, touch input, and physical gestures (such as those used in some video games). The Voice Browser Working Group and the Multimodal Interaction Working Group are coordinating their efforts to make the Web available on more devices and in more situations.

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 --
Ian Jacobs, <ij@w3.org>, +1.718.260.9447
Contact Europe, Africa and the Middle East --
Marie-Claire Forgue, <mcf@w3.org>, +33.492.38.75.94
Contact Asia --
Fumihiro Kato <fumi@w3.org>, +81.466.49.1170

Testimonials for "W3C Standard Simplifies Creation of Speech-Enabled Web Applications" Press Release

Loquendo · Openstream · VoiceXML Forum


As leader in multilingual speech technologies and voice platforms, Loquendo believes that PLS 1.0 will simplify the creation of both Speech Synthesis and Speech Recognition applications - for the widest number of integrators and users, and in all languages. Pronunciation transcriptions can be incorporated into a single PLS Lexicon Document - rather than being distributed throughout the SSML documents or SRGS grammars - and Pronunciation Lexicons can then be reused and shared between different applications and with other application developers. This means that PLS 1.0 will enable prompt creators and service designers to create VoiceXML applications more rapidly, more easily, and with improved pronunciation and recognition accuracy - and all this is possible in any language, bringing all the benefits of standards to multilanguage voice applications.

From its very beginnings, Loquendo has been an active participant in the support and development of standards, and the company is very pleased to have authored the PLS specification, and will continue to give its full support to W3C Voice Browser and Multimodal Interaction Working Groups, as well as VoiceXML Forum activities, firmly believing in the competitive edge that being standards compliant brings.

-- Daniele Sereno, Vice President Product Engineering, Loquendo


As one of the leading developers of open-standards based multimodal platform & speech-enabled mobile applications globally and as one of the early & active contributors to the W3C's discussions on Multimodal Interaction & Voice Browser development, Openstream is very pleased at the release of PLS 1.0 as a W3C Recommendation. PLS 1.0 is an important landmark in the standardization and offers us a powerful mechanism in personalization of speech interfaces.

-- Raj Tumuluri, President, Openstream Inc.

VoiceXML Forum

The VoiceXML Forum endorses the Recommendation of the W3C and its Voice Browser Working Group for the Pronunciation Lexicon Specification 1.0 (PLS 1.0) standard. Like the widely-adopted VoiceXML standard, the forthcoming PLS standard will drive the adoption of speech technologies and reduce the costs of deploying speech solutions.

-- Rob Marchand, Chairman, VoiceXML Forum

Related RSS feed