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.
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?
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?