HyperAIHyperAI초신경
홈뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Speech Separation On Wham

평가 지표

SI-SDRi

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
SI-SDRi
Paper TitleRepository
TDANet Large15.2An efficient encoder-decoder architecture with top-down attention for speech separation
WHYV12.964An alternative Approach in Voice Extraction-
MossFormer (L) + DM17.3MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
TDANet14.8An efficient encoder-decoder architecture with top-down attention for speech separation
MossFormer218.1MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
SepReformer-L + DM18.4Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
0 of 6 row(s) selected.