# GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets

arXiv: https://arxiv.org/abs/2609.37798 · HTML: https://mlsanity.com/paper/2609.37798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 29 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [Multi-task self-supervised learning for Robust Speech Recognition](https://mlsanity.com/paper/2001.09239/) (2020)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [Unsupervised pretraining transfers well across languages](https://mlsanity.com/paper/2002.02848/) (2020)
- [DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization](https://mlsanity.com/paper/2012.06659/) (2020)
- [A-JEPA: Joint-Embedding Predictive Architecture Can Listen](https://mlsanity.com/paper/2311.15830/) (2023)
- [When Does LeJEPA Learn a World Model?](https://mlsanity.com/paper/2605.26379/) (2026)
- [Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning](https://mlsanity.com/paper/2507.02915/) (2025)
- [USAD: Universal Speech and Audio Representation via Distillation](https://mlsanity.com/paper/2506.18843/) (2025)
- [WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms](https://mlsanity.com/paper/2509.23238/) (2025)
- [MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization](https://mlsanity.com/paper/2306.08463/) (2023)
- [S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2606.19398/) (2026)

## Abstract (arXiv)

Speech self-supervised learning aims to learn general-purpose representations for downstream speech tasks. However, current approaches rely on complex, carefully designed prediction targets. We challenge this necessity with GLaS-JEPA, a framework that directly predicts the current encoder's continuous representations at masked positions, without contrastive learning, discrete targets, or separate EMA target encoders. We prevent representation collapse using SIGReg representation-space regularization, eliminating the need for engineered target-generation mechanisms. Pretrained on 960 hours of LibriSpeech, our 57M-parameter model achieves a 6.89% WER on frozen-encoder SUPERB ASR and a 25.87% CER on slot filling, outperforming the best non-distilled sub-90M baselines by 43.1% and 22.0%, respectively. These results demonstrate that highly competitive speech representations can emerge from a radically simplified training recipe.