반응형
[Paper 리뷰] DQ-Data2Vec: Decoupling Quantization for Multilingual Speech Recognition
DQ-Data2Vec: Decoupling Quantization for Multilingual Speech RecognitionData2Vec의 masked representation generation은 multi-layer averaging에 의존적임DQ-Data2Vec$K$-means quantizer를 사용하여 masked prediction을 위한 language, phoneme information을 decoupling특히 quantization을 shallow, middle layer 모두에 적용하여 irrelevant feature를 explicitly decoupling논문 (TASLP 2025) : Paper Link1. IntroductionXLSR과 같은 Self-Supervise..
Paper/Representation
2026. 1. 15. 14:13
반응형