SHoUT is a toolkit for performing research on large vocabulary continuous speech recognition (LVCSR). The toolkit contains applications for training statistical models and for speech/non-speech detection, speaker diarization and decoding.
- Large Vocabulary Continuous Speech Recognition
- Acoustic Model training
- Speaker adaptation (VTLN, CMN/CVN, SMAPLR)
- speaker diarization
- speech/non-speech classification
CategoriesHuman Machine Interfaces
Follow The "SHoUT" speech recognition toolkit
Rate This ProjectLogin To Rate This Project
There are no 3 star reviews.