# Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space

arXiv: https://arxiv.org/abs/2606.01909 · HTML: https://mlsanity.com/paper/2606.01909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (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)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks](https://mlsanity.com/paper/2012.14952/) (2020)
- [End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors](https://mlsanity.com/paper/2005.09921/) (2020)
- [Masked Modeling Duo: Towards a Universal Audio Pre-training Framework](https://mlsanity.com/paper/2404.06095/) (2024)
- [Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning](https://mlsanity.com/paper/2507.02915/) (2025)
- [TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings](https://mlsanity.com/paper/2303.03849/) (2023)
- [EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers](https://mlsanity.com/paper/2203.17068/) (2022)
- [PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings](https://mlsanity.com/paper/2403.02288/) (2024)

## Abstract (arXiv)

We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and then specialised by stages to carry speaker identity, phonetic content, and dynamic source routing in the same 512-dimensional latent space, with no per-task fine-tuning at deployment. Light heads handle diarization (ArcFace + VBx) and dynamic source separation (null-target K-set prediction). On synthetic VoxCeleb2 mixtures with unknown K, the canonical stack reaches 15.00% blind DER, 97.80% PIT separation accuracy with +9.52 dB latent SI-SDR, and a +53.50-point speaker/content factorisation gap on a held-out k-NN probe. The point of Echo is not a new SOTA on any single task but the joint coexistence of three tasks on one encoder at this footprint. We document the design stage by stage, report the dead-ends, and identify the structural wall on end-to-end ASR through the VQ bottleneck that still bounds the PoC.