HyperAI超神经

首页资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Speech Separation On Wsj0 3Mix

评估指标

SI-SDRi

评测结果

各个模型在此基准测试上的表现结果

模型名称	SI-SDRi	Paper Title	Repository
Gated DualPathRNN	16.85	Voice Separation with an Unknown Number of Multiple Speakers
Sandglasset	17.1	Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
MossFormer (M) + DM	20.8	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
MossFormer (L) + DM	21.2	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SepTDA	23.7	Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor	-
Separate And Diffuse	20.9	Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation	-
MossFormer2	22.2	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
SepIt	20.1	SepIt: Approaching a Single Channel Speech Separation Bound	-
SepFormer	19.5	Attention is All You Need in Speech Separation

0 of 9 row(s) selected.