search

mravanelli / pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
2.36k stars 446 forks source link

How to train/decode on reverberant speech? #251

Open kevinmchu opened 3 years ago

kevinmchu commented 3 years ago

I'd like to train a model on reverberant speech using the alignments generated from the corresponding anechoic data. Currently, I'm doing something similar to TIMIT_joint_training_liGRU_fbank.cfg, where I am using the reverberant TIMIT recipe to extract the features and the anechoic recipe for lab_folder and lab_graph. I noticed that decode_dnn.sh uses the lab_graph to generate the lattice rather than the graph constructed from the reverberant acoustic model.

What is the easiest way to specify using the anechoic alignments and reverberant graph?

kevinmchu commented 3 years ago

I just wanted to follow up an ask if anyone has suggestions.