* VXML and SALT help extend voice apps' reach
Voice or speech recognition applications have been around for awhile. Our Special Focus this week takes a look at the technology, one that more companies and carriers are using because speech recognition is getting better. Our author writes that more powerful processors and refined algorithms are at the core of the improvement.
Voice or speech recognition applications have been around for awhile. Our Special Focus this week takes a look at the technology, one that more companies and carriers are using because speech recognition is getting better.
Our author writes that more powerful processors and refined algorithms are at the core of the improvement.
Now, at the application-development level, two new specifications that extend current markup languages are helping enterprises and service providers get in the door:
* Voice Extensible Markup Language (VXML) is an extension of XML that lets developers take advantage of work that has already been done to put applications and information on the Web. Released in Version 1.0 in 2000, it is now in Version 2.0. VXML has opened up the voice-based market to new vendors, such as start-up VoiceGenie Technologies, while leading existing vendors to offer alternatives to their proprietary software platforms using VXML interpreter software.
* Speech Application Language Tags (SALT), backed by Microsoft, Cisco and Intel, also is coming on the scene. It is based on extensions of scripting languages including HTML and XML. The software giant released the first beta of its SALT-based Speech Server in July, but it’s currently marketing the platform directly to enterprises and not to service providers.
Speech recognition makes it practical to do things with a phone that would be too complicated using the 12-digit keypad. In some cases this means the end of callers being forced to work their way through a hierarchy of options by pressing numbers or saying particular words. Though not at the point in which systems can understand anything a caller might say, callers no longer have to use specific words. Voice recognition can also trigger transactions without the need for a live operator. Combined with speech-to-text and text-to-speech technology, it can support even more emerging applications.
For more on this story see https://www.nwfusion.com/news/2003/0811carrspecialfocus.html
