- Large Vocabulary Continuous Speech Recognition system.
- Realtime speech recognition on a 2GHz processor for up to 256000 word vocabularies.
- Language identified automatically. Transcriptions returned in native or romanized script.
- Language models and grammars can be externally specified (defaults are provided).
- Speaker independent recognition
- Environmental noise compensation can be user activated
- Endpoints for significant acoustic events
- Optimal performance for speech captured over closetalking and farfield microphones (for telephony applications, we recommend our LV VSR system)
|
Released Sept 06
.
|