Research map / Probabilistic and scientific modeling / Dynamical systems
Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy Environments
Daniel Johnson, Daniel Gorelik, Ross E Mawhorter, Kyle Suver, Weiqing Gu, Steven Xing, Cody Gabriel, Peter Sankhagowit
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use LGAP instead of MESSL, DALAS and the independent tied-microphone baseline | LGAP · Synthetic anechoic Common Voice mixtures | location squared error | Improved |
| use independent tied-microphone model instead of LGAP in small regions with few sources | independent tied-microphone baseline · Synthetic anechoic Common Voice mixtures | mask precision and recall | No clear effect |
| grow region size and add sources for the independent tied-microphone baseline | independent tied-microphone baseline · Synthetic anechoic Common Voice mixtures | separation quality | Hurt |
| increase number of microphone pairs | LGAP · Synthetic anechoic Common Voice mixtures | precision | Improved |
| increase number of sources | LGAP and all baselines · Synthetic anechoic Common Voice mixtures | separation performance | Hurt |
| increase region size from 4 m to 512 m | LGAP · Synthetic anechoic Common Voice mixtures | separation and localization performance | No clear effect |
| use only a small number of microphone pairs | LGAP · Synthetic anechoic Common Voice mixtures | separation performance | No clear effect |
Closest papers by meaning
- The Cone of Silence: Speech Separation by Localization (NeurIPS 2020 · similarity 0.87)
- Mix and Localize: Localizing Sound Sources in Mixtures (CVPR 2022 · similarity 0.86)
- Action Dubber: Timing Audible Actions via Inflectional Flow (ICML 2025 · similarity 0.84)
- ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior (ICML 2025 · similarity 0.83)
- Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge (CVPR 2024 · similarity 0.83)
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.82)
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.
