# Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search

arXiv: https://arxiv.org/abs/2609.31024 · HTML: https://mlsanity.com/paper/2609.31024/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation](https://mlsanity.com/paper/2211.04772/) (2022)
- [Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching](https://mlsanity.com/paper/2506.07199/) (2025)
- [SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding](https://mlsanity.com/paper/2506.17815/) (2025)
- [LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives](https://mlsanity.com/paper/2607.00784/) (2026)
- [FM Synthesizer Audio-Parameter Shared Embeddings](https://mlsanity.com/paper/2608.18226/) (2026)

## Abstract (arXiv)

Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often difficult to optimize, while direct search requires rendering every candidate. We introduce Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data. At inference, candidate parameters are scored directly in this learned space, yielding a renderer-free objective whose audio geometry is shaped by parameter correspondences rather than generic audio similarity. We evaluate Synth-JEPA on Surge XT using held-out synthesizer sounds and out-of-domain NSynth and FSD50K targets, against inverse models, direct search, and learned proxy objectives. Synth-JEPA outperforms all baselines in-domain and remains competitive out-of-domain. Its matching quality continues to improve with additional test-time search, allowing compute to be traded for match quality. In pairwise listening tests, listeners preferred Synth-JEPA in 85% of trials overall. Together, these results show that an audio representation with a parameter-induced geometry allows synthesizer sound matching to be approached as an effective renderer-free search problem.