GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
eess.AS, cs.AI, cs.LG, cs.SD
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
- A-JEPA: Joint-Embedding Predictive Architecture Can Listen
- WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms
- When Does LeJEPA Learn a World Model?
Related papers
- Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
- X-VC: Zero-shot Streaming Voice Conversion in Codec Space
- Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
- VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation
- Conditional Flow Matching for Visually-Guided Acoustic Highlighting
- Anonymization, Not Elimination: Utility-Preserved Speech Anonymization