HyperAIHyperAI초신경
홈뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Speech Separation On Wsj0 3Mix

평가 지표

SI-SDRi

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
SI-SDRi
Paper TitleRepository
Gated DualPathRNN16.85Voice Separation with an Unknown Number of Multiple Speakers
Sandglasset17.1Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
MossFormer (M) + DM20.8MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
MossFormer (L) + DM21.2MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SepTDA23.7Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor-
Separate And Diffuse20.9Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation-
MossFormer222.2MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
SepIt20.1SepIt: Approaching a Single Channel Speech Separation Bound-
SepFormer19.5Attention is All You Need in Speech Separation
0 of 9 row(s) selected.