# Arti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis

arXiv: https://arxiv.org/abs/2609.09757 · HTML: https://mlsanity.com/paper/2609.09757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [A multispeaker dataset of raw and reconstructed speech production real-time MRI video and 3D volumetric images](https://mlsanity.com/paper/2102.07896/) (2021)
- [Deep Speech Synthesis from MRI-Based Articulatory Representations](https://mlsanity.com/paper/2307.02471/) (2023)
- [Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speech](https://mlsanity.com/paper/2409.15525/) (2024)
- [Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition](https://mlsanity.com/paper/2505.24059/) (2025)
- [Interpretable Modeling of Articulatory Temporal Dynamics from real-time MRI for Phoneme Recognition](https://mlsanity.com/paper/2509.15689/) (2025)

## Abstract (arXiv)

Real-time MRI (rtMRI) captures the dynamics of the entire vocal tract during speech, but labeled data are scarce and the modality - single-slice, grayscale, low-resolution - differs substantially from the natural videos that video foundation models are trained on. We introduce Arti-JEPA, a joint embedding predictive architecture to model vocal tract rtMRI by continuing its self-supervised objective on about 62h of unlabelled vocal-tract videos, and evaluate the frozen representation on three tasks: cross-domain phoneme prediction (on typical speakers), fluent-vs-disfluent classification (a corpus containing stuttered speech), and characterizing pre/post-operative transfer (after partial glossectomy). Three key findings emerge. (1) A temporal video prior decisively outperforms per-frame image encoders, and latent prediction (V-JEPA) is at least as strong as pixel reconstruction (VideoMAE), with the edge on fine-grained phonemes. (2) Domain adaptation is task-dependent: it roughly doubles cross-domain phoneme prediction kappa (to 0.352) but does not help binary stuttering classification. (3) Arti-JEPA was able to recover phoneme signal from pre/post glossectomy speech --- an in-domain probe decodes patients at least as well as a typical speaker, indicating that the residual transfer gap is cross-speaker/domain misalignment, not surgical signal loss, and post-operative decoding does not fall below performance on pre-operative speech. Together, these position a frozen, domain-adapted rtMRI encoder as a reusable measurement tool for articulatory and clinical speech science.