AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SAM Audio: Segment Anything in Audio

Bowen Shi, Andros Tjandra, John Hoffman, Helin Wang, YI-CHIAO WU, Luya Gao, Julius Richter, Matthew Le, Apoorv Vyas, Sanyuan Chen, Christoph Feichtenhofer, Piotr Dollár and 2 more

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 0 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 ground-truth span to text prompt (ablation)SAM Audio · General soundOVR subjective score: 3.32 -> 4.04Improved
use span prompt alone instead of text on music (ablation)SAM Audio · MusicOVR subjective score: 4.09 -> 2.57Hurt
use span prompt alone instead of text on general sound (ablation)SAM Audio · General soundOVR subjective score: 3.32 -> 3.54Improved
add PEA-Frame predicted spans to text prompting (ablation)SAM Audio · General SFXOVR subjective score: 3.36 -> 3.89Improved
add PEA-Frame predicted spans to text prompting (ablation)SAM Audio · SpeakerOVR subjective score: 3.62 -> 4.01Improved
add PEA-Frame predicted spans to text prompting (ablation)SAM Audio · Instrument (pro, MUSDB)OVR subjective score: 4.16 -> 4.12Hurt
add predicted spans to text prompting (ablation)SAM Audio · SpeechOVR subjective score: 4.17 -> 4.22No clear effect
use predicted spans instead of ground-truth spans (ablation)SAM Audio · text+span promptingOVR subjective scoreNo clear effect
use visual prompt instead of text promptSAM Audio · General SFXOVR subjective score: 3.59 (text) -> 2.61 (visual)Hurt
SAM Audio over specialized modelstext-prompted separation · Instrument (pro, MUSDB)OVR subjective score: 4.28 -> 4.45Improved
use SAM Audio Judge instead of CLAP/SDR estimator/Gemini as metricreference-free evaluation · SpeechPearson correlation with humans: 0.490 -> 0.883Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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