The 2011 Speech Luminaries

Steward of Standards
Dan Burnett
Director of Speech Technologies and Standards at Voxeo

Estimates suggest that 85 percent of IVR systems deployed in North America and Western Europe use VoiceXML and Speech Synthesis Markup Language (SSML). A new version of SSML—ushered in by Dan Burnett, director of speech technologies and standards at Voxeo, in September—has exposed even more markets to the language.

SSML 1.1, which Burnett spearheaded as co-chair of the Voice Browser Working Group of the World Wide Web Consortium (W3C), extends speech on the Web to an enormous new market by improving support for Asian languages and multilingual voice applications. SSML 1.1 also provides control over voice selection and such speech characteristics as pronunciation, volume, and pitch. What’s more, TTS control is extended to more parameters. The trimming attribute, for example, enables different extracts of prompts or audio files to be rendered according to context.

“With SSML 1.1, there is an intentional focus on Asian language support, including Chinese languages, Japanese, Thai, Urdu, and others, to provide a wide deployment potential,” Burnett says. “With SSML 1.0, we already had strong traction in North America and Western Europe, so this focus makes SSML 1.1 incredibly strong globally.”

The multilingual 1.1 enhancements stem from discussions Burnett led in China, Greece, and India. He “organized and led an international team of experts to sift through requirements, analyze alternative strategies, and define extensions that enable SSML to represent the various aspects of human language pronunciation,” says Jim Larson, co-chair of the W3C Voice Browser Working Group. “I believe Dan has brought the world a little closer together by helping to create a single computer language that can represent how people speak around the world.”

“The SSML specification is a significant development for application developers and technology integrators working around speech, as it hugely simplifies the creation of speech-based applications on the Web and elsewhere,” Paolo Baggia, director of international standards at Loquendo and coauthor of the standard, said in a statement.

Burnett is no stranger to standards development. During the past nine years, he has led many speech recognition efforts in the W3C. For example, he served as editor of VoiceXML 2.0, 2.1, and 3.0.
—Leonard Klie

(THIRD OF FOUR PAGES)