# Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures

arXiv: https://arxiv.org/abs/2602.09040 · HTML: https://mlsanity.com/paper/2602.09040/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [Neural Networks Fail to Learn Periodic Functions and How to Fix It](https://mlsanity.com/paper/2006.08195/) (2020)
- [Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning](https://mlsanity.com/paper/2410.19560/) (2024)
- [Collapse-Proof Non-Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2410.04959/) (2024)
- [Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities](https://mlsanity.com/paper/2401.11143/) (2024)
- [Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders](https://mlsanity.com/paper/2409.00391/) (2024)

## Built on by (most cited first, 1 of 1)

- [Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA](https://mlsanity.com/paper/2608.19084/) (2026)

## Abstract (arXiv)

Joint Embedding Predictive Architectures (JEPA) offer a promising approach to self-supervised speech representation learning, but suffer from representation collapse without explicit grounding. We propose GMM-Anchored JEPA, which fits a Gaussian Mixture Model once on log-mel spectrograms and uses its frozen soft posteriors as auxiliary targets throughout training. A decaying supervision schedule allows GMM regularization to dominate early training before gradually yielding to the JEPA objective. Unlike HuBERT and WavLM, which require iterative re-clustering, our approach clusters input features once with soft rather than hard assignments. On ~50k hours of speech, GMM anchoring improves ASR (28.68% vs. 33.22% WER), emotion recognition (67.76% vs. 65.46%), and slot filling (64.7% vs. 59.1% F1) compared to a WavLM-style baseline with matched compute. Cluster analysis shows GMM-anchored representations achieve up to 98% entropy compared to 31% for WavLM-style, indicating substantially more uniform cluster utilization. Code is made available at https://github.com/gioannides/clustering-anchored-jepa.