Word alignments based on character-level attention maps in Whisper with unsupervised head selection.

A C++ implementation of unigram tokenization

End-to-End Speech Recognition Using Tensorflow

Fast and differentiable hidden Markov model in C++

Code for Autoregressive Co-training for Learning Discrete Representations https://arxiv.org/abs/2203.15840

[ICASSP20] A Dialogical Emotion Decoder For Speech Emotion Recognition in Spoken Dialog

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

[ICASSP19] An Interaction-aware Attention Network for Speech Emotion Recognition in Spoken Dialogs

[Interspeech19] Computational Paralinguistics ChallengE (ComParE)

Interspeech 2018 Computational Paralinguistics ChallengE (ComParE): Self-Assessed Affect recognition sub-challenge