Research map / Vision-language and multimodal / Cross-modal learning
Neural-Inspired Modeling of Auditory Selection and Compensation for Audio-Visual Speech Separation
Xinmeng Xu, Haoran Xie, Xiaohui Tao, Lin Li, S. Joe Qin
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 |
|---|---|---|---|
| add auditory selection module (ASM) (ablation) | Neuro-SCNet · LRS2-4Mix | SI-SNRi (dB): 8.6 -> 9.8 | Improved |
| add auditory selection module (ASM) (ablation) | Neuro-SCNet · LRS2-2Mix | SI-SNRi (dB): 16.4 -> 17.2 | Improved |
| add cross-modal compensation module (CCM) (ablation) | Neuro-SCNet · LRS2-4Mix | SI-SNRi (dB): 8.4 -> 9.8 | Improved |
| add cross-modal compensation module (CCM) (ablation) | Neuro-SCNet · LRS2-2Mix | SI-SNRi (dB): 16.2 -> 17.2 | Improved |
| add both ASM and CCM (ablation) | Neuro-SCNet · LRS2-4Mix | SI-SNRi (dB): 7.0 -> 9.8 | Improved |
| use estimated phase instead of mixture phase (ablation) | Neuro-SCNet · LRS2-4Mix | SI-SNRi (dB): 6.5 -> 9.8 | Improved |
| use oracle clean phase instead of learned phase (ablation) | Neuro-SCNet · LRS2-2Mix | SI-SNRi (dB): 17.2 -> 17.5 | Improved |
| add audio encoder alongside joint encoder (ablation) | Neuro-SCNet · LRS2-4Mix | SI-SNRi (dB): 8.1 -> 9.8 | Improved |
| use parallel magnitude and phase decoders instead of single-domain modeling (ablation) | Neuro-SCNet · LRS2-3Mix | SI-SNRi (dB): 11.5 -> 13.9 | Improved |
| add visual pre-alignment offset estimation and reliability weighting (ablation) | visual path · LRS2 at 200 ms shift | SI-SNRi (dB): 14.8 -> 16.2 | Improved |
| add reliability weighting to offset-only alignment at zero shift (ablation) | visual path · LRS2 at 0 ms shift | SI-SNRi (dB): 16.9 -> 17.2 | Improved |
| use Neuro-SCNet instead of IIANet with four speakers | IIANet · LRS2-4Mix | SI-SNRi (dB): 8.2 -> 9.8 | Improved |
Closest papers by meaning
- An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits (TPAMI 2024 · similarity 0.89)
- Modeling Attention and Memory for Auditory Selection in a Cocktail Party Environment (AAAI 2018 · similarity 0.88)
- Continual Audio-Visual Sound Separation (NeurIPS 2024 · similarity 0.87)
- Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization (NeurIPS 2025 · similarity 0.87)
- RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation (ICLR 2024 · similarity 0.86)
- AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs (ICML 2026 · similarity 0.85)
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.
