A collection of scripts based on Kaldi for speech recognition, diarization & language modeling
Speech Recognition asr
-
- Data prep
-
- Lexicon generation
-
- Grammar generation (pocolm & srilm)
-
- Feature extraction
-
- HMM-GMM training
-
- Data augmentation (speed, volume, reverb, music, noise, babble)
-
- Embedding (i-vector, x-vector)
-
- DNN training
-
- RNNLM training
-
- Rescoring
Diarization diarization
-
- i-vector (LIUM)
-
- x-vector (Kaldi)
(c) 2020 Sylvain Le Groux [email protected]