COG-MHEAR Audio-Visual Speech Enhancement Challenge

Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation (INTERSPEECH 2020)

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar

Python wrappers for Kaldi data