Tutorials
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
wav2vec 2.0 changed the game with contrastive self-supervision, but HuBERT asked a sharper question: what if we skip the contrastive trick entirely and just do…
Tutorials
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self Supervise
Why choose between contrastive learning and masked language modeling for speech pretraining when you can wire both into the same network?
Tutorials
Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition
Speech emotion recognition has long been stuck with tiny labeled datasets and hand-crafted acoustic features.
Tutorials
Joint Unsupervised and Supervised Training for Multilingual ASR
Pretrain-then-finetune has become the default recipe for multilingual ASR, but it leaves a lot on the table: the two stages don't share losses, and the supervi…
Tutorials
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Most speech SSL models optimize for ASR and hope everything else works out.