VoxSigma
| Developer(s) | Vocapia Research |
|---|---|
| Stable release | 2.0 / August 2010 |
| Operating system | Linux, Mac OS X |
| Type | Speech-to-text |
| License | Proprietary |
| Website | http://www.vocapia.com |
VoxSigma is a speech recognition software suite developed by Vocapia Research for Unix-like x86 and x86-64 platforms.
History
The VoxSigma software suite has its roots at LIMSI, a French CNRS laboratory conducting research on speech processing since the 70s. VoxSigma is the latest generation of speech processing offered by Vocapia Research, building upon accurate statistical modeling techniques developed at LIMSI for speech production and speech perception. The first commercial version was released in July 2003.
Features
The VoxSigma suite offers large vocabulary speech-to-text capabilities[1] [2] in multiple languages. It includes adaptive features allowing the transcription of noisy speech, such as speech over background music. The software suite has been designed for professional users needing to transcribe large quantities of audio and video documents such as broadcast data, either in batch mode or in real-time. Versions can also be used to transcribe call-center data.
The speech-to-text processing result is a fully annotated XML document including labels for speech and non-speech segments, speaker labels, words with time codes and high quality confidence scores. This XML file can be directly indexed by a search engine, or alternatively can be converted into plain text with capitalization and punctuation.
The VoxSigma suite is also available as a Web service.
Supported languages: Arabic, Dutch, English, Finnish, French, German, Greek, Italian, Mandarin, Polish, Portuguese, Romanian, Russian, Spanish.