yjw123456

Audio-visual-Overlapped-speech-recognition

Ovelapped speech recognition

BayesRNNLM

Bayesian Neural Network Language Model

e2e_lfmmi

This is the implementation of paper CONSISTENT TRAINING AND DECODING FOR END-TO-END SPEECH RECOGNITIONUSING LATTICE-FREE MMI submitted to ICASSP2022

MultiChannel_AVSR

sudo_rm_rf

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.