Voice XML Overview James A Larson Intel Corporation

Voice. XML Overview James A. Larson Intel Corporation jim@larson-tech. com (c) 2007 Larson Technical Services 1

Outline • Motivation for Voice. XML • W 3 C Speech Interface Framework Languages • Dialog—Voice. XML 2. 0 • Speech Synthesis—SSML • Grammars—SRGS • Semantic Interpretation—SI • Voice. XML 2. 1 (c) 2007 Larson Technical Services 2

Voice. XML in the Marketplace • Voice. XML 2. 0 is now ratified as a Recommendation (e. g. , official standard) by the W 3 C • Hundreds of millions of Voice. XML calls are answered every day Voice. XML is the standard for building speech-enabled applications (c) 2007 Larson Technical Services 3

Motivation for Speech Applications • Users access Web sites from any telephone, anywhere, any time. • Speaking and listening are the natural usage modes for phones. (c) 2007 Larson Technical Services 4

Strength of Voice. XML Applications • Traditional system-directed dialogs for novice users • Mixed initiative dialogs for experienced users • Novice users smoothly become experienced users at their own pace (c) 2007 Larson Technical Services 5

Limitations of Voice. XML Applications • No special analysis of speech input – Not suitable for training speech skills— Reading, ESL, singing, etc. • VUI conversational bandwidth is slower than GUI conversational bandwidth – Using a VUI is like drinking from Lake Superior with a straw (c) 2007 Larson Technical Services 6

Exercise 1 • Name or describe a speech application you could use at work. • Name or describe a speech application you or family member can use at home. (c) 2007 Larson Technical Services 7

XML • XML = e. Xtensible Markup Language • Elements are surrounded by tags Welcome to the voice system • Elements may be nested Welcome to Ajax Travel we have the cheapest fares • Elements may have attributes • Because “<”, “>”, and “&” have special meanings “< ” in place of “<” “> ” in place of “>” “& ” in place of “&”. (c) 2007 Larson Technical Services 8

Outline • Motivation for Voice. XML • W 3 C Speech Interface Framework Languages • Dialog—Voice. XML 2. 0 • Speech Synthesis—SSML • Grammars—SRGS • Semantic Interpretation—SI • Voice. XML 2. 1 (c) 2007 Larson Technical Services 9

Documents Multimedia Files HTML Scripts DB Database Server Voice. XML Scripts Grammars Audio Files Web Browser Capture Voice ASR Voice DTMF Browser Replay Audio TTS Speech Server/Gateway Web Server (c) 2007 Larson Technical Services 10

W 3 C Speech Interface Framework Voice. XML 2. 0 Speech Synthesis Call Control Other Semantic Interpretation (c) 2007 Larson Technical Services Grammar 11

Status of W 3 C Speech Interface Languages Recommendation Proposed Recommendation Candidate Recommendation Last Call Working Draft Semantic Interpret. Ration Voice Grammar Synthesis (SISR) XML 2. 0 (SRGS) (SSML) Working Draft Requirements (c) 2007 Larson Technical Services Call Control (CCXML) Voice XML 2. 1 V 3 12

Outline • Motivation for Voice. XML • W 3 C Speech Interface Framework Languages • Dialog—Voice. XML 2. 0 • Speech Synthesis—SSML • Grammars—SRGS • Semantic Interpretation—SI • Voice. XML 2. 1 (c) 2007 Larson Technical Services 13

Example of Voice. XML 2. 0 Fragment Dialog Language (Vocie. XML 2. 0) Speech Synthesis Markup Language (SSML) Speech Recognition Grammar Specification (SRGS) … Semantic Interpretation (SI) Which account savings or checking savings checking CD certificate of deposit $ = “CD” …. (c) 2007 Larson Technical Services 14 …

Example of Voice. XML 2. 0 Fragment Dialog Language (Vocie. XML 2. 0) Speech Synthesis Markup Language (SSML)

Example of Voice. XML 2. 0 Fragment Dialog Language (Vocie. XML 2. 0) Speech Synthesis Markup Language (SSML)

Example of Voice. XML 2. 0 Fragment Dialog Language (Vocie. XML 2. 0) Speech Synthesis Markup Language (SSML)

Voice. XML 2. 0 features • Menus, forms, sub-dialogs • – , , , , –