Speech Server 2004 FAQs
Home

Q1: What is Microsoft® Speech Server 2004?

Microsoft Speech Server 2004 (MSS) combines Web technologies, speech-processing services, and telephony capabilities into a single, integrated system.
Built on the robust and scalable Windows Server™ 2003 operating system and the powerful Visual Studio® .NET development environment, Speech Server enables companies to unify their Web and telephony infrastructure, and extend existing or new ASP.NET Web applications for speech-enabled access from telephones, mobile phones, Pocket PCs, and Smartphones. Speech Server is a flexible and integrated speech platform that dramatically reduces the complexity and cost of developing and deploying speech applications.

Q2: How is Speech Server 2004 different from desktop dictation speech recognition?

Microsoft Speech Server is used to build and deploy Web-based Interactive Voice Response (IVR) applications accessed by the telephone, as well as Web-based multimodal (mixed speech/visual) applications accessed by mobile devices over a wireless network. Speech Server provides neither command and control of desktop applications, nor speech-to-text dictation capabilities.

Q3: What does Speech Server include 'in-the-box'?

Microsoft Speech Server 2004 is the only speech platform to comprehensively support Web-based touchtone (DTMF) and speech-enabled IVR applications, as well as multimodal applications, and includes speech application development tools, Microsoft's enterprise-grade Automatic Speech Recognition (ASR) engine, the ScanSoft® Speechify™ Text-to-Speech (TTS) engine, a prompt engine, a SALT Interpreter (voice browser), and telephony services.

Note: For connecting Speech Server to a telephone system (e.g. a PBX), third-party telephony interface software and an Intel® telephony card are required. Please contact Intel or Intervoice for more information.

Q4: How is Speech Server different from other speech platforms?

Microsoft Speech Server is the only speech platform that provides a comprehensive set of features, tools, and components for creating speech-enabled IVR, touchtone, and multimodal applications.
Speech Server, unlike most other speech platforms, was specifically designed to take advantage of the power and ubiquity of Web technologies, using a Web-based development model and deploying on a Web infrastructure.

Q5: How does Speech Server integrate into my existing IT infrastructure?

Speech-enabled Web applications for Speech Server deploy on your existing ASP.NET Web server and are accessed over the LAN or IP network by Speech Server for telephony-based applications, or via a mobile device over a wireless network for multimodal applications.

Q6: What does a Speech Server deployment look like?

The basic Speech Server development and deployment topology is as follows:

1) Visual Studio .NET and the Speech Application SDK (SASDK) on a separate development workstation;

2) a Web server for hosting your speech applications; and

3) Microsoft Speech Server which includes Telephony Application Services (TAS) and Speech Engine Services (SES) providing key telephony, audio/media, speech recognition, prompt, and speech synthesis services for SALT-based speech applications. For telephony voice-only applications Speech Server connects to a telephone system via a third-party software interface called a Telephony Interface Manager (TIM) and a telephony card. Mobile devices connect to Speech Server-based multimodal applications over a wireless 802.11b (Wi-Fi) connection.

Home