← Speech Separation

Papers with Code · CC BY-SA 4.0

WHAMR!

아카이브 평가 18건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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 (M)	SI-SDRi 18.5 SDRi 16.9 Number of parameters (M) 15	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
TF-Locoformer (S)	SI-SDRi 17.4 SDRi 15.9 Number of parameters (M) 5	TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 2024-08-06	코드 1
SepReformer-L + DM	SI-SDRi 17.1	Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation 2024-06-10	코드 1
MossFormer2	SI-SDRi 17.0	MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation 2023-12-19	코드 1 · 코드 2
MossFormer (L) + DM	SI-SDRi 16.3	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
TD-Conformer (XL) + DM	SI-SDRi 14.6	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 2023-10-09	코드 1
Improved Sudo rm -rf (U=36)	SI-SDRi 13.5	Compute and memory efficient universal sound source separation 2021-03-03	코드 1 · 코드 2 · 코드 3
TD-Conformer (L) + DM	SI-SDRi 13.4	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 2023-10-09	코드 1
Wavesplit	SI-SDRi 13.2	Wavesplit: End-to-End Speech Separation by Speaker Clustering 2020-02-20	연결 없음
DPTNET - SRSSN	SI-SDRi 12.3	Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain 2021-10-10	연결 없음
DPRNN - SRSSN	SI-SDRi 12.3	Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain 2021-10-10	연결 없음
VSUNOS	SI-SDRi 12.2	Voice Separation with an Unknown Number of Multiple Speakers 2020-02-29	코드 1 · 코드 2 · 코드 3 · 코드 4
Sudo rm -rf (U=16)	SI-SDRi 12.1	Sudo rm -rf: Efficient Networks for Universal Audio Source Separation 2020-07-14	코드 1 · 코드 2 · 코드 3 · 코드 4
TD-Confomer (M) + DM	SI-SDRi 12	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 2023-10-09	코드 1
Deformable TCN + Dynamic Mixing	SI-SDRi 11.1 SDRi 10.3 Number of parameters (M) 3.6 MACs (G) 3.7	Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation 2022-10-27	코드 1 · 코드 2
TD-Confomer (S)	SI-SDRi 10.5	On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 2023-10-09	코드 1
Deformable TCN + Shared Weights + Dynamic Mixing	SI-SDRi 10.1 SDRi 9.5 Number of parameters (M) 1.3 MACs (G) 3.7	Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation 2022-10-27	코드 1 · 코드 2
Bi-LSTM-TASNET	SI-SDRi 9.2	WHAM!: Extending Speech Separation to Noisy Environments 2019-07-02	코드 1