Software enables voice access to e-business applications.
Press Release Summary:
WebSphere® Voice Server for Multiplatforms v4.2 with third-generation synthesized speech Concatenative Text-to-Speech (CTTS) offers female voice for U.S. English, French, German, and Japanese as well as U.K. English male and female voice when using WebSphere Voice Response for AIX. Software also offers Dutch speech recognition and Korean language speech recognition with CTTS male voice. Female voice for Cantonese, Dutch, Korean, and Italian languages is also offered.
Original Press Release:
IBM WebSphere Voice Server V4.2 Extends WebSphere Voice Server V3.1.1, Enhancing the Enablement of Voice Access to e-business Applications and Data
At a glance
WebSphere Voice Server for Multiplatforms V4.2 includes all the capability of WebSphere Voice Server V3.1.1, and provides the following new features:
More natural sounding synthesized speech with the new third-generation synthesized speech Concatenative Text-to-Speech (CTTS) with:
o An additional female voice for the U.S. English
o New French, German, and Japanese female voices
o The addition of a U.K. English male and female voice when using WebSphere Voice Response for AIX
o Dutch speech recognition when using WebSphere Voice Response for AIX, and the availability of ScanSoft RealSpeak Dutch TTS
o Korean language speech recognition and CTTS male voice when using WebSphere Voice Response for AIX
o Availability of ScanSoft RealSpeak TTS for Cantonese, Dutch, Korean, and Italian languages for female voice on AIX
Overview
WebSphere® Voice Server (WVS) for Multiplatforms V4.2 extends the WVS V3.1.1 product, and delivers additional customer-focused enhancements:
o Additional third-generation CTTS voice (female voice) for U.S. English on WebSphere Voice Response for AIX®
o Third-generation CTTS voices for U.K. English and Japanese on WebSphere Voice Response for AIX
o Dutch language speech recognition on WebSphere Voice Response for AIX and the availability of ScanSoft RealSpeak TTS female voice on AIX
o Korean language speech recognition and third-generation CTTS (male voice) on WebSphere Voice Response for AIX
o The availability of ScanSoft RealSpeak TTS for Cantonese, Dutch, Korean, and Italian languages for female voice on AIX
o VoiceXML V2 Browser shipped on WebSphere Voice Response for AIX V3.1 VoiceXML V2 and Java(TM) Enhancements electronic image CD Part number C506ZNA, which is compatible with WebSphere Voice Server for Multiplatforms V4.2
o Support for VoiceXML 2.0, Speech Recognition Grammar Specification (SRGS) 1.0, Speech Synthesis Markup Language (SSML) 1.0, and Semantic Interpretation for Speech Recognition (SISR) 1.0 when using WebSphere Voice Response for AIX
Key prerequisites
Passport Advantage® agreement
A Single-Byte Character System (SBCS) operating system
Note: Double-Byte Character System (DBCS) support for AIX 5.1 is required for WebSphere Voice Server V4.2 for AIX for Cantonese, Korean, Japanese, and Simplified Chinese. For details, refer to the Hardware requirements and Software requirements sections.
Planned availability dates
September 26, 2003: Electronic software and documentation delivery for all WVS V4.2 products except those listed below:
November 21, 2003: Electronic software and documentation delivery for ScanSoft RealSpeak Cantonese, Korean, and Italian languages CTTS for WebSphere Voice Server
October 24, 2003: Media and documentation for all WVS V4.2 products except those listed below:
December 19, 2003: Media and documentation for ScanSoft RealSpeak Cantonese, Korean, and Italian languages and Korean CTTS for WebSphere Voice Server
Description
WebSphere Voice Server (WVS) for Multiplatforms V4.2 includes:
o Speech recognition software that can listen to words spoken over a telephone, recognize these words, and pass the recognized words as text to an application
o TTS software that synthesizes speech from application text for play-back over a telephone
o Connection to many telephony platforms, including WebSphere Voice Response for AIX and WebSphere Voice Response for Windows(TM) (formerly known as DirectTalk® for AIX and DirectTalk for Windows), Intel(TM) Dialogic, Cisco or Siemens HiPath, and Voice Server Speech Technologies for Windows and Linux
o Development tools, including support for applications written in VoiceXML 2.0, Java Beans, or C
o Complimentary copies of the following products:
-Voice Toolkit V4.2 for WebSphere Studio
-WebSphere Studio Site Developer V5 for Windows
WVS V4.2 is a software product that can be integrated with other software and hardware telephony products to speech-enable these products.
A customer using an application developed with WebSphere Voice Server places a telephone call from either a landline or mobile phone.
A telephony server answers this telephone call, which is a PC or UNIX® server with special telephony hardware that allows it to answer telephone calls.
The telephony server is also running WebSphere Voice Server, which listens to the user speaking and recognizes words.
These recognized words are then passed to the application, running on WebSphere Application Server, which performs the desired transaction and sends the resulting text back to the WebSphere Voice Server.
The WVS then uses the text to synthesize speech, which the telephony server routes back to the handset where the caller can hear it.
