반응형
[Paper 리뷰] Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
Metis: A Foundation Speech Generation Model with Masked Generative Pre-trainingMasked Generative Modeling을 활용하여 다양한 speech generation task에 fine-tuning 되는 speech foundation model을 구성할 수 있음MetisSelf-Supervised Learning token과 acoustic token에 대한 2가지 discrete speech representation을 활용Additional condition 없이 300K hours의 speech data에 대해 masked generative pre-training을 수행논문 (NeurIPS 2025) : Paper Link..
Paper/Representation
2025. 11. 17. 13:06
반응형