Performance Characterizations for Speech Applications: Microsoft Speech Server and Intel Telephony Servers
Click here to download now
Overview: Improvements in speech technology and the increased use of PDAs, mobile voice, and multi-modal devices are combining to propel the development and deployment of speech-enabled applications. Incorporating speech as a viable user interface offers a degree of flexibility to users who previously have been limited to fix-placed Web browsers or hierarchical Interactive voice response (IVR) menu schemes. Automatic Speech Recognition (ASR) and Text-To-Speech (TTS) are two of the baseline services that make it possible to extend application user interfaces beyond Web browser and touchtone (DTMF) interactions.

