Papers › On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant...

On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments

9 Oct 2023arXiv:2310.06125archive 2025-07-28

William Ravenscroft, Stefan Goetze, Thomas Hain

Speech separation remains an important topic for multi-speaker technology researchers. Convolution augmented transformers (conformers) have performed well for many speech processing tasks but have been under-researched for speech separation. Most recent state-of-the-art (SOTA) separation models have been time-domain audio separation networks (TasNets). A number of successful models have made use of dual-path (DP) networks which sequentially process local and global information. Time domain conformers (TD-Conformers) are an analogue of the DP approach in that they also process local and global context sequentially but have a different time complexity function. It is shown that for realistic shorter signal lengths, conformers are more efficient when controlling for feature dimension. Subsampling layers are proposed to further improve computational efficiency. The best TD-Conformer achieves 14.6 dB and 21.2 dB SISDR improvement on the WHAMR and WSJ0-2Mix benchmarks, respectively.

PaperPDFCode

Code

jwr1995/pubsep officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencySpeech Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Separation WHAMR! TD-Conformer (XL) + DM SI-SDRi 14.6 #6 of 18 Archive leaderboard report
Speech Separation WHAMR! TD-Conformer (L) + DM SI-SDRi 13.4 #8 of 18 Archive leaderboard report
Speech Separation WHAMR! TD-Confomer (M) + DM SI-SDRi 12 #14 of 18 Archive leaderboard report
Speech Separation WHAMR! TD-Confomer (S) SI-SDRi 10.5 #16 of 18 Archive leaderboard report
Speech Separation WSJ0-2mix TD-Conformer (XL) + DM SI-SDRi 21.2 #21 of 40 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

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