Research map / Label-efficient and robust learning / Self-supervised and contrastive
Toward a realistic model of speech processing in the brain with self-supervised learning
Juliette MILLET, Charlotte Caucheteux, Pierre Orhan, Yves Boubenec, Alexandre Gramfort, Ewan Dunbar, Christophe Pallier, Jean-Remi King
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 |
|---|---|---|---|
| Use self-supervised instead of supervised (phoneme CTC) training on same 600h speech (ablation) | wav2vec 2.0 · fMRI brain score, 412 participants | brain score R: \Delta R = 0.002 | Improved |
| Train on non-speech sounds instead of random initialization (ablation) | wav2vec 2.0 · fMRI brain score | brain score R: \Delta R = 0.006 | Improved |
| Train on non-native speech instead of non-speech sounds (ablation) | wav2vec 2.0 · fMRI brain score | brain score R: \Delta R=0.002 | Improved |
| Train on native language speech instead of non-native speech (ablation) | wav2vec 2.0 · fMRI brain score | brain score R: \Delta R=0.002 | Improved |
| Train wav2vec 2.0 (any) instead of random initialization (ablation) | wav2vec 2.0 · fMRI brain score | brain score R | Improved |
Closest papers by meaning
- The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning (ICML 2025 · similarity 0.93)
- Improving Semantic Understanding in Speech Language Models via Brain-tuning (ICLR 2025 · similarity 0.88)
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models (NeurIPS 2025 · similarity 0.88)
- LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale (NeurIPS 2026 · similarity 0.87)
- SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph Encoding (NeurIPS 2026 · similarity 0.87)
- RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain (NeurIPS 2026 · similarity 0.87)
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.
