Papers with Code · CC BY-SA 4.0

WSJ0-2mix

아카이브 평가 40건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
TF-Locoformer (L) + DM	SI-SDRi 25.1 SDRi 25.2 Number of parameters (M) 22.5	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
SepReformer-L	SI-SDRi 25.1 SDRi 25.2 Number of parameters (M) 59.4 MACs (G) 155.5	Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation 2024-06-10	코드 1
TF-Locoformer (M) + DM	SI-SDRi 24.6 SDRi 24.7 Number of parameters (M) 15.0	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
TF-Locoformer (L)	SI-SDRi 24.2 SDRi 24.3 Number of parameters (M) 22.5	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
MossFormer2 (L)	SI-SDRi 24.1 Number of parameters (M) 55.7	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation 2023-12-19	코드 1 · 코드 2
SepTDA (L=12)	SI-SDRi 24.0	Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor 2024-01-23	연결 없음
Separate And Diffuse	SI-SDRi 23.9	Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation 2023-01-25	연결 없음
TF-Locoformer (M)	SI-SDRi 23.6 SDRi 23.8 Number of parameters (M) 15.0	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
TF-Locoformer (S) + DM	SI-SDRi 22.8 SDRi 23 Number of parameters (M) 5.0	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
MossFormer (L) + DM	SI-SDRi 22.8 Number of parameters (M) 42.1 MACs (G) 86.1	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions 2023-02-23	코드 1 · 코드 2
SepMamba + DM (M)	SI-SDRi 22.7 SDRi 22.9	SepMamba: State-space models for speaker separation using Mamba 2024-10-28	코드 1
SPGM + DM	SI-SDRi 22.7 Number of parameters (M) 26.2 MACs (G) 77	SPGM: Prioritizing Local Features for enhanced speech separation performance 2023-09-22	코드 1
MossFormer (M) + DM	SI-SDRi 22.5	MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions 2023-02-23	코드 1 · 코드 2
SepIt	SI-SDRi 22.4	SepIt: Approaching a Single Channel Speech Separation Bound 2022-05-24	연결 없음
SepFormer	SI-SDRi 22.3 SDRi 22.4	Attention is All You Need in Speech Separation 2020-10-25	코드 1 · 코드 2 · 코드 3 · 코드 4
Wavesplit v2	SI-SDRi 22.2 SDRi 22.3	Wavesplit: End-to-End Speech Separation by Speaker Clustering 2020-02-20	연결 없음
SPGM	SI-SDRi 22.1 Number of parameters (M) 26.2 MACs (G) 77	SPGM: Prioritizing Local Features for enhanced speech separation performance 2023-09-22	코드 1
TF-Locoformer (S)	SI-SDRi 22 SDRi 22.1 Number of parameters (M) 5.0	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
DPTNet (Libri1Mix speech enhancement pre-trained)	SI-SDRi 21.3 SDRi 21.5	Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training 2020-10-29	코드 1
SepMamba + DM (S)	SI-SDRi 21.2 SDRi 21.4	SepMamba: State-space models for speaker separation using Mamba 2024-10-28	코드 1
TD-Conformer (XL) + DM	SI-SDRi 21.2	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 2023-10-09	코드 1
Sandglasset	SI-SDRi 21.0	Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation 2021-03-01	코드 1 · 코드 2
GALR	SI-SDRi 20.3	Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks 2021-01-13	코드 1 · 코드 2
DPTNet	SI-SDRi 20.2	Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation 2020-07-28	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
Gated DualPathRNN	SI-SDRi 20.12	Voice Separation with an Unknown Number of Multiple Speakers 2020-02-29	코드 1 · 코드 2 · 코드 3 · 코드 4
Sudo rm -rf (U=36)	SI-SDRi 19.5	Compute and memory efficient universal sound source separation 2021-03-03	코드 1 · 코드 2 · 코드 3
Wavesplit v1	SI-SDRi 19.0	Wavesplit: End-to-End Speech Separation by Speaker Clustering 2020-02-20	연결 없음
Sudo rm -rf XL	SI-SDRi 18.9	Sudo rm -rf: Efficient Networks for Universal Audio Source Separation 2020-07-14	코드 1 · 코드 2 · 코드 3 · 코드 4
Dual-path RNN	SI-SDRi 18.8	Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation 2019-10-14	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
DeepCASA	SI-SDRi 17.7	Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation 2019-04-25	코드 1