Methods › Audio › Speech Separation Models › SepFormer

SepFormer

12 papers tagged archive 2025-07-28

Introduced by Cem Subakan et al. in Attention is All You Need in Speech Separation

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SepFormer is Transformer-based neural network for speech separation. The SepFormer learns short and long-term dependencies with a multi-scale approach that employs transformers. It is mainly composed of multi-head attention and feed-forward layers. A dual-path framework (introduced by DPRNN) is adopted and RNNs are replaced with a multiscale pipeline composed of transformers that learn both short and long-term dependencies. The dual-path framework enables the mitigation of the quadratic complexity of transformers, as transformers in the dual-path framework process smaller chunks.

The model is based on the learned-domain masking approach and employs an encoder, a decoder, and a masking network, as shown in the figure. The encoder is fully convolutional, while the decoder employs two Transformers embedded inside the dual-path processing block. The decoder finally reconstructs the separated signals in the time domain by using the masks predicted by the masking network.

PaperSource

Papers archive 2025-07-28

12 shown of 12, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

11 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Speech Separation9
Decoder2
Speech Enhancement2
Speech Extraction2
All1
Audio Source Separation1
Denoising1
Generalization Bounds1
Multi-Speaker Source Separation1
Speaker Verification1
Target Speaker Extraction1

Usage over time archive 2025-07-28

Papers per year tagged with SepFormer: 2020 to 2025, peak 5 5 0 2020: 1 paper 2020 2021: 1 paper 2021 2022: 2 papers 2022 2023: 5 papers 2023 2024: 2 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (12 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Speech Separation Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections