Tag
CAFE提出将CKA特征蒸馏的梯度限制在英语旁路的语言路由适配器中,解决了多语言紧凑ASR中英语与非英语WER的权衡问题,在Open ASR Leaderboard上将平均WER从8.55%降至8.02%。
OmniVAE is a jointly trained audio-video VAE that uses segment-level contrastive learning and feature distillation to align latent spaces, improving joint generation quality and synchronization in text-to-audio-video generation.