반응형
[Paper 리뷰] Robust Data2Vec: Noise-Robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning
Robust Data2Vec: Noise-Robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive LearningContrastive learning과 regression task에 기반한 self-supervised pre-training method를 통해 Automatic Speech Recognition 성능을 향상할 수 있음Robust Data2VecPre-training stage에서 contrastive learning과 regression task를 jointly optimizing추가적으로 patch-based non-semantic negative sample과 positiv..
Paper/Representation
2025. 4. 11. 18:31
반응형