AI Paper Atlas

Research map / Video / Video generation

Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Wei Guo, Heng Wang, Jianbo Ma, Weidong Cai

AAAI 2026 · Video › Video generation · approach: Video-to-audio synthesis · 12 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 CMSS manifold embeddings to the Remixer input (ablation)SS2A · VGG-SS multi-sourceSSMS: 1.579 -> 5.973Improved
add CMSS manifold embeddings to the Remixer input (ablation)SS2A · VGG-SS single-sourceC-FAD: 122.127 -> 15.150Improved
add CLIP embeddings alongside CMSS in the Remixer input (ablation)SS2A · VGG-SS single-sourceC-FAD: 96.045 -> 15.150Improved
add CLIP embeddings alongside CMSS in the Remixer input (ablation)SS2A · VGG-SS multi-sourceSSMS: 5.553 -> 5.973Improved
add CCMR mask regularization (alpha=0.35) (ablation)SS2A · VGG-SS multi-sourceSSMS: 1.342 -> 5.973Improved
increase CCMR alpha from 0.35 to 1 (ablation)SS2A · VGG-SS multi-sourceSSMS: 5.973 -> 4.237Hurt
add Cycle Mix (sample size 64, iterations 64) (ablation)SS2A · VGG-SS multi-sourceSSMS: 5.868 -> 5.973Improved
add Cycle Mix (sample size 64, iterations 64) (ablation)SS2A · VGG-SS single-sourceSSMS: 5.048 -> 4.936Hurt
use 4 attention layers instead of 1 in the Remixer (ablation)SS2A · VGG-SS multi-sourceSSMS: 5.973 -> 5.395Hurt
use 4 attention layers instead of 1 in the Remixer (ablation)SS2A · VGG-SS single-sourceC-FAD: 15.150 -> 14.021Improved
use CMSS variant B instead of shallower variant A (ablation)SS2A · VGG-SS multi-sourceSSMS: 4.868 -> 5.973Improved
use CMSS variant B instead of deeper variant C (ablation)SS2A · VGG-SS multi-sourceSSMS: 4.763 -> 5.973Improved

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