Research map / Architectures and efficiency / Attention and transformers
Modeling Attention and Memory for Auditory Selection in a Cocktail Party Environment
Jiaming Xu, Jing Shi, Guangcan Liu, Xiuyi Chen, Bo Xu
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 |
|---|---|---|---|
| replace life-long memory with a speaker embedding matrix (ASAM-spk) (ablation) | ASAM · WSJ0 two-speaker, top-down | GNSDR: 7.46 -> 8.16 | Mixed |
| replace life-long memory with a speaker embedding matrix (ASAM-spk) (ablation) | ASAM · WSJ0 two-speaker plus street noise | GNSDR: 4.36 -> 3.92 | Hurt |
| use ASAM instead of deep clustering without noise threshold under real noise | DC · WSJ0 two-speaker plus street noise | GNSDR: 2.61 -> 4.36 | Improved |
| use ASAM instead of best DC (-40) on clean two-speaker mixtures | DC (-40) · WSJ0 two-speaker | GNSDR: 7.47 -> 7.46 | No clear effect |
| use ASAM instead of DC (-40) on three-speaker THCHS-30 | DC (-40) · THCHS-30 three-speaker | GNSDR: 5.48 -> 5.02 | Hurt |
| add background noise threshold to deep clustering (-40 dB) | DC · WSJ0 two-speaker | GNSDR: 4.78 -> 7.47 | Improved |
| longer stimulus duration for unknown speaker memory (ablation) | ASAM · bottom-up attention, two unknown speakers | GNSDR | Improved |
Closest papers by meaning
- SALMONN: Towards Generic Hearing Abilities for Large Language Models (ICLR 2024 · similarity 0.84)
- Continual Audio-Visual Sound Separation (NeurIPS 2024 · similarity 0.84)
- AND: Audio Network Dissection for Interpreting Deep Acoustic Models (ICML 2024 · similarity 0.84)
- S$^2$M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection (NeurIPS 2025 · similarity 0.84)
- Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models (ICLR 2026 · similarity 0.83)
- Weakly-supervised Audio Separation via Bi-modal Semantic Similarity (ICLR 2024 · similarity 0.83)
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.
