The World Wide Web Consortium (W3C) announced new work on extensions to components of the Speech Interface Framework which will both extend Speech Synthesis Markup Language functionality to Asian and other languages, and include speaker verification features into the next version of VoiceXML, version 3.0. Addressing both areas expands both the reach and functionality of the framework.
Working Group Internationalizing SSML
The Speech Synthesis Markup Language (SSML), a W3C Recommendation since 2004, is designed to provide a rich, XML-based markup language for assisting the generation of synthetic speech in Web and other applications. The essential role of the markup language is to provide authors of synthesizable content a standard way to control aspects of speech such as pronunciation, volume, pitch, rate, etc. across different synthesis-capable platforms.
While these attributes are critical, additional attributes may be even more important to specific languages. For example, Mandarin Chinese, the most widely spoken language in the world today, also has the notion of tones - the same written character can have multiple pronunciations and meanings based on the tone used. Given the profusion of cellphones in China - some estimate as high as over one billion - the case for extending SSML for Mandarin is clear in terms of sheer market forces. Including extensions for Japanese, Korean and other languages will ensure that a fuller participation possible of the world on the Web.
Speaker Verification Extension to Be Included in VoiceXML 3.0
Another feature users are demanding of telephony services and the Web is speaker verification.
"Identity theft, fraud, phishing, terrorism, and even the high cost of resetting passwords have heightened interest in deploying biometric security for all communication channels, including the telephone,” said Ken Rehor of Vocalocity, newly elected Chairman of the VoiceXML Forum and participant in the W3C Voice Browser Working Group. “Speaker verification and identification is not only the best biometric for securing telephone transactions and communications, it can work seamlessly with speech recognition and speech synthesis in VoiceXML deployments."
Until now, most vendors have compensated for this missing feature by making a custom fix for their services. The result has been a set of divergent technologies that do not interoperate. Thanks to requirements contributions from the VoiceXML Forum's Speaker Biometrics Committee, the W3C Voice Browser Working Group has been able to identify the features needed for a standardized speech verification module. The Working Group is now beginning to address these requirements.
Timing Perfect for New Participants
Given the depth and breadth of the announced new work, as well as plans for additional features for VoiceXML 3.0, this is a perfect time for new companies, researchers and other interested parties to join W3C and participate in the latest developments for voice technologies and the Web. Among potential critical contributors are those from the research and industrial sectors throughout Asia in the areas of Asian languages and speaker verification, to allow for the best possible expertise in the development of standards that truly serve the needs of Web users worldwide. More information on the W3C Voice Browser Activity and on joining W3C is on the W3C Web site.
About the World Wide Web Consortium [W3C]
The W3C was created to lead the Web to its full potential by developing common protocols that promote its evolution and ensure its interoperability. It is an international industry consortium 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. Services provided by the Consortium include: a repository of information about the World Wide Web for developers and users, and various prototype and sample applications to demonstrate use of new technology. Over 400 organizations are Members of the Consortium. For more information see http://www.w3.org/
Working Group Internationalizing SSML
The Speech Synthesis Markup Language (SSML), a W3C Recommendation since 2004, is designed to provide a rich, XML-based markup language for assisting the generation of synthetic speech in Web and other applications. The essential role of the markup language is to provide authors of synthesizable content a standard way to control aspects of speech such as pronunciation, volume, pitch, rate, etc. across different synthesis-capable platforms.
While these attributes are critical, additional attributes may be even more important to specific languages. For example, Mandarin Chinese, the most widely spoken language in the world today, also has the notion of tones - the same written character can have multiple pronunciations and meanings based on the tone used. Given the profusion of cellphones in China - some estimate as high as over one billion - the case for extending SSML for Mandarin is clear in terms of sheer market forces. Including extensions for Japanese, Korean and other languages will ensure that a fuller participation possible of the world on the Web.
Speaker Verification Extension to Be Included in VoiceXML 3.0
Another feature users are demanding of telephony services and the Web is speaker verification.
"Identity theft, fraud, phishing, terrorism, and even the high cost of resetting passwords have heightened interest in deploying biometric security for all communication channels, including the telephone,” said Ken Rehor of Vocalocity, newly elected Chairman of the VoiceXML Forum and participant in the W3C Voice Browser Working Group. “Speaker verification and identification is not only the best biometric for securing telephone transactions and communications, it can work seamlessly with speech recognition and speech synthesis in VoiceXML deployments."
Until now, most vendors have compensated for this missing feature by making a custom fix for their services. The result has been a set of divergent technologies that do not interoperate. Thanks to requirements contributions from the VoiceXML Forum's Speaker Biometrics Committee, the W3C Voice Browser Working Group has been able to identify the features needed for a standardized speech verification module. The Working Group is now beginning to address these requirements.
Timing Perfect for New Participants
Given the depth and breadth of the announced new work, as well as plans for additional features for VoiceXML 3.0, this is a perfect time for new companies, researchers and other interested parties to join W3C and participate in the latest developments for voice technologies and the Web. Among potential critical contributors are those from the research and industrial sectors throughout Asia in the areas of Asian languages and speaker verification, to allow for the best possible expertise in the development of standards that truly serve the needs of Web users worldwide. More information on the W3C Voice Browser Activity and on joining W3C is on the W3C Web site.
About the World Wide Web Consortium [W3C]
The W3C was created to lead the Web to its full potential by developing common protocols that promote its evolution and ensure its interoperability. It is an international industry consortium 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. Services provided by the Consortium include: a repository of information about the World Wide Web for developers and users, and various prototype and sample applications to demonstrate use of new technology. Over 400 organizations are Members of the Consortium. For more information see http://www.w3.org/
