Research map / Label-efficient and robust learning / Recognition and long-tail
Trainable EEG Interpolation and Structure-Sharing Dual-Path Encoders for Brain-Assisted Target Speaker Extraction
Zhao Lv, Haoran Zhou, Ying Chen, Youdian Gao, Xinhui Li, Ruibo Fu, Cunhang Fan
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 trainable EEG interpolation (TEI) over fixed interpolation (ablation) | baseline TSE model · Cocktail Party | SI-SDR (dB): 14.10 -> 15.48 | Improved |
| add SSDPE to EEG encoder only (ablation) | baseline TSE model · Cocktail Party | SI-SDR (dB): 14.10 -> 15.28 | Improved |
| add SSDPE to speech encoder only (ablation) | baseline TSE model · Cocktail Party | SI-SDR (dB): 14.10 -> 14.28 | Improved |
| add SSDPE to both encoders without TEI (ablation) | baseline TSE model · Cocktail Party | SI-SDR (dB): 14.10 -> 15.31 | Improved |
| add TEI on top of SSDPE in both encoders (ablation) | SSDPE both encoders · Cocktail Party | SI-SDR (dB): 15.31 -> 15.63 | Improved |
| add SSDPE in one encoder on top of TEI (ablation) | TEI-only model · Cocktail Party | SI-SDR (dB): 15.48 -> 15.35 (EEG only), 15.30 (speech only) | Hurt |
| add SSDPE to both encoders on top of TEI (ablation) | TEI-only model · Cocktail Party | SI-SDR (dB): 15.48 -> 15.63 | Improved |
| add TEI and SSDPE (full TIDENet) versus M3ANet | brain-assisted TSE · AVED | SI-SDR (dB): 10.89 -> 13.31 | Improved |
| full TIDENet versus M3ANet | brain-assisted TSE · Cocktail Party | SI-SDR (dB): 13.95 -> 15.63 | Improved |
| add TEI plus SSDPE in speech encoder only versus full model (ablation) | TIDENet · Cocktail Party | ESTOI: 85.07% (#7) vs 82.93% (#8) | Mixed |
Closest papers by meaning
- SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph Encoding (NeurIPS 2026 · similarity 0.85)
- The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning (ICML 2025 · similarity 0.85)
- Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals (NeurIPS 2024 · similarity 0.85)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.84)
- CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings (NeurIPS 2026 · similarity 0.83)
- LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale (NeurIPS 2026 · 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.
