AI Paper Atlas

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

SoundSpaces: Audio-Visual Navigation in 3D Environments

Changan Chen, Unnat Jain, Carl Schissler, Sebastia Vicenc Amengual Gari, Ziad Al-Halah, Vamsi Krishna Ithapu, Philip Robinson, and Kristen Grauman

ECCV 2020 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 230 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 audio (AudioPointGoal vs PointGoal)Blind agent · ReplicaSPL: 0.480 -> 0.681Improved
add audio (AudioPointGoal vs PointGoal)RGB agent · ReplicaSPL: 0.521 -> 0.632Improved
add audio (AudioPointGoal vs PointGoal)Depth agent · ReplicaSPL: 0.601 -> 0.709Improved
add audio (AudioPointGoal vs PointGoal)Blind agent · Matterport3DSPL: 0.426 -> 0.473Improved
add audio (AudioPointGoal vs PointGoal)RGB agent · Matterport3DSPL: 0.466 -> 0.521Improved
add audio (AudioPointGoal vs PointGoal)Depth agent · Matterport3DSPL: 0.541 -> 0.581Improved
use spectrograms instead of intensity-only audio input (ablation)AudioGoal Depth · ReplicaSPL: 0.291 -> 0.756Improved
use spectrograms instead of intensity-only audio input (ablation)AudioGoal Depth · Matterport3DSPL: 0.014 -> 0.552Improved
add 40dB SNR microphone noiseAudioGoal Depth · ReplicaSPL: 0.756 -> 0.753No clear effect
add 40dB SNR microphone noiseAudioGoal Depth · Matterport3DSPL: 0.552 -> 0.550No clear effect
test on unheard instead of same soundsAudioGoal Depth · ReplicaSPL: 0.756 -> 0.454Hurt
test on unheard instead of same soundsAudioPointGoal Depth · ReplicaSPL: 0.709 -> 0.707No clear effect

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