AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Sound Localization by Self-Supervised Time Delay Estimation

Ziyang Chen, David F. Fouhey, Andrew Owens

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add augmentation (noise, reverb, mixture) (ablation)StereoCRW on FMA · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.434 -> 0.133Improved
add augmentation (ablation)MonoCLR on FMA · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.430 -> 0.187Improved
add augmentation (ablation)ZeroNCE on FMA · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.227 -> 0.174Improved
add augmentation (ablation)StereoCRW on FAIR · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.241 -> 0.174Improved
add augmentation (ablation)StereoCRW on FMA · In-the-wild left/right (885 clips)accuracy (%): 82.2 -> 87.2Improved
add augmentation (ablation)MonoCLR on FMA · In-the-wild left/right (885 clips)accuracy (%): 83.8 -> 87.4Improved
add augmentation (ablation)ZeroNCE on FMA · In-the-wild left/right (885 clips)accuracy (%): 85.4 -> 85.6No clear effect
add augmentation (ablation)Salvati et al. on Vox-Sim · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.126 -> 0.169Hurt
use cycle-consistent random walk (StereoCRW) instead of slow-feature loss (ZeroNCE)stereo self-supervised model trained on FMA · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.174 -> 0.133Improved
train on large FMA (101K clips) instead of FAIR-PlayStereoCRW with augmentation · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.174 -> 0.133Improved
train on stereo sounds (ZeroNCE) instead of mono (MonoCLR) without augmentationself-supervised model on FMA · TDE-Simulation (SNR 10, RT60 0.5s)MAE (ms): 0.430 -> 0.227Improved
add visual input (AV model) to StereoCRW (ablation)StereoCRW · Visually-guided TDE (0.96s)RMSE (ms): 0.493 -> 0.304Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy