DeepMind's AudioFM hits best results on 10 of 12 audio tasks, beats prior SSL on heart murmur by +4.7 F1
iScienceLuvr · x · 2026-10-27
Google DeepMind researchers introduced AudioFM, a self-supervised framework for general-purpose audio representation learning (arXiv:2610.34183).
- Method: combines recording-level contrastive learning with patch-wise masked latent discrimination — a student predicts representations of time/frequency-masked spectrogram patches and picks the matching full-view EMA-teacher target from candidates in other recordings, with weaker supervision from masked temporal neighbors for local consistency.
- Results: best or joint-best linear-probing performance on 10 of 12 tasks, with SOTA event detection, scene understanding, and domain generalizability.
- Highlight: outperforms prior audio SSL on medical audio — +4.7 F1 on heart murmur and +3.2 F1 on sleep apnea subtype classification, underscoring the promise of audio foundation models in medical AI.
Related event: DeepMind Releases AudioFM, Achieving SOTA on 10 of 12 Audio Tasks(2 posts)→
More from Multimodal
- AI-Generated SNEEEKERS Concept Sneakers Look Like Real Product Shots — Delahuntagram · 2026-10-28
- Creator chains Halo and Runway via MCP connectors in GPT for a music video workflow — aziz4ai · 2026-10-28
- Kling AI 4.0 to power animated feature 'Minibots' from Evolutionary Films, set for 2027 — CurieuxExplorer · 2026-10-28
- Independent Egyptian filmmaker crafts cinematic Ramses II documentary with AI tools — Automatic_Client7403 · 2026-10-28
- KlingAI 4.0 recreates Austin Powers scene where Vanessa fails to take him out — AdImpossible8653 · 2026-10-28
- Volumetric light shafts in PlayCanvas: Gaussian splats cast their own shadow map, no proxy geometry — willeastcott · 2026-10-28