Wav2vec2
1 mentions across 0 people
All mentions
Unknown speaker
Recommendedpaper · 2026-06-11
“we fine-tune and compare pretrained self-supervised speech models (Wav2Vec2 and HuBERT) on data from two click-rich Khoisan languages (G|ui and West !Xoon)”
Self-Supervised Speech Models Generalize to Uncommon Click Consonants ↗