Microsoft Releases Speech Server 2007 Beta

REDMOND, Wash. — Microsoft Corp. released the Microsoft® Speech Server 2007 beta and a new set of features. Scheduled for release in fall 2006, Speech Server 2007 is Microsoft's next-generation speech and telephony platform.

Speech Server 2007, the third release of Microsoft's speech and telephony platform, will include tools for the application development process from start to finish as well as next-generation speech recognition capabilities based on statistical modeling. Details of the new features include the following:

• Advisor Technology in Speech Server 2007 provides guidance during authoring and refinement of the grammar, which is the vocabulary of a speech-enabled application. The Grammar Tuning Advisor clusters unrecognized words. After tuning an application, developers can validate their improvements against actual caller responses to identify any new issues.
• Conversational Understanding a developer to create conversational grammars by typing or importing example phrases.
• Dialog Workflow Designer, based on the Windows® Workflow Foundation (http://msdn.microsoft.com/workflow), provides a drag-and-drop tool for designing applications and call flows. The end result is a Microsoft .NET assembly that is expressed visually in a Visio®-style diagram. Because it is based on the Workflow Foundation, the Dialog Workflow Designer can initiate other workflows including business rules, back-end operations or Web services calls.

With Speech Server 2007, developers will have a range of options to build speech applications including Speech Application Language Tags (SALT), Voice Extensible Markup Language (VoiceXML), or a Microsoft .NET Framework-based language to build voice response applications; native support for session initiation protocol (SIP) to support IP contact centers; and extensible analysis and business intelligence tools.

Speech Server 2007 will be a global release with support for touchtone applications around the world and speech-enabled applications in Canadian French, English (U.S. and U.K.), German, and U.S. Spanish at launch. Using the "language pack" expansion capability built into Speech Server 2007, additional languages can be introduced independently over time.

Developers can apply for the Speech Server 2007 beta or take advantage of the resources available to learn more about Speech Server, including webcasts, case studies and newsletters. The official Microsoft Speech Server team blog "You Talkin to Me" is also now available at http://blogs.msdn.com/mssblog.