Papers › RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

29 Sep 2023arXiv:2309.17189archive 2025-07-28

Samuel Pegg, Kai Li, Xiaolin Hu

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA) models operate in the time domain. However, their overly simplistic approach to modeling acoustic features often necessitates larger and more computationally intensive models in order to achieve SOTA performance. In this paper, we present a novel time-frequency domain audio-visual speech separation method: Recurrent Time-Frequency Separation Network (RTFS-Net), which applies its algorithms on the complex time-frequency bins yielded by the Short-Time Fourier Transform. We model and capture the time and frequency dimensions of the audio independently using a multi-layered RNN along each dimension. Furthermore, we introduce a unique attention-based fusion technique for the efficient integration of audio and visual information, and a new mask separation approach that takes advantage of the intrinsic spectral nature of the acoustic features for a clearer separation. RTFS-Net outperforms the prior SOTA method in both inference speed and separation quality while reducing the number of parameters by 90% and MACs by 83%. This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2309.17189")

Code

Syntology Ran 0 of 1 code samples harvested from 1 repository linked to this paper; 1 has no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

spkgyk/RTFS-Net officialmentioned 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

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from spkgyk/RTFS-Net. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

MultiModalFusion spkgyk/RTFS-Net/src/models/TDAVNet/fusion.py official repository unverified MIT (permissive) · 7b8df33b830a890a · report

Tasks

Audio-Visual Speech RecognitionSpeech RecognitionSpeech SeparationTarget Speaker Extractionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Separation LRS2 RTFS-Net-12 SDRi 15.1 #4 of 8 Archive leaderboard report
Speech Separation LRS2 RTFS-Net-12 SI-SNRi 14.9 #4 of 8 Archive leaderboard report
Speech Separation LRS2 RTFS-Net-6 SDRi 14.8 #5 of 8 Archive leaderboard report
Speech Separation LRS2 RTFS-Net-6 SI-SNRi 14.6 #5 of 8 Archive leaderboard report
Speech Separation LRS2 RTFS-Net-4 SDRi 14.3 #7 of 8 Archive leaderboard report
Speech Separation LRS2 RTFS-Net-4 SI-SNRi 14.1 #7 of 8 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-12 SDRi 17.6 #2 of 5 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-12 SI-SNRi 17.5 #2 of 5 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-6 SDRi 17.1 #4 of 5 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-6 SI-SNRi 16.9 #4 of 5 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-4 SDRi 15.6 #5 of 5 Archive leaderboard report
Speech Separation LRS3 RTFS-Net-4 SI-SNRi 15.5 #5 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-12 SDRi 13.6 #2 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-12 SI-SNRi 12.4 #2 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-6 SDRi 12.8 #4 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-6 SI-SNRi 11.8 #4 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-4 SDRi 12.4 #5 of 5 Archive leaderboard report
Speech Separation VoxCeleb2 RTFS-Net-4 SI-SNRi 11.5 #5 of 5 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

SPEED

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