Wizzard Software announces the release of WizzScribe SI (Speaker Independent) for Linux, significantly expanding WizzScribe's market coverage to include Linux platforms as well as applications where speaker independence (i.e. no training required) is a priority.

WizzScribe offerings from Wizzard, which are powered by proven and leading-edge speech recognition technologies from IBM, now include the newly announced WizzScribe Speaker Independent version for Linux, as well as Wizzard's original WizzScribe Speaker Dependent version for Windows. Both offerings offer exceptional accuracy and are designed for developers to implement as offline conversions of voice audio into text, bringing large vocabulary voice recognition technology to a new generation of business applications.

Through the use of an offline (deferred, a.k.a. speak now, reco later) batch mode of voice recognition, WizzScribe SI for Linux can support a wide variety of input devices and methods, and can add speech recognition capability to "industrial strength" server-based applications whenever large volumes of audio need to be converted into text for searching, data-mining, storage, analysis and information archiving. This new technology incorporates a conversational model, thus eliminating the dependence on user training and punctuation as normally seen in traditional dictation models, and embodies a basic simplicity of implementation that does not require an SDK.

"Wizzard is very pleased to be able to introduce a new version of WizzScribe that we believe will address many of the large scale opportunities that have been brought to us," said Bruce Phifer, General Manager of Technology and Services for Wizzard. "WizzScribe SI for Linux is based on new technology that produces exceptional accuracy in large vocabulary speaker independent environments, even via telephony, and we are looking forward to showcasing it in our booth at SpeechTEK in August."