# Self-Supervised Test-Time Tuning for Packet Loss Concealment

arXiv: https://arxiv.org/abs/2607.01823 · HTML: https://mlsanity.com/paper/2607.01823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [Zero-Shot Self-Supervised Learning for MRI Reconstruction](https://mlsanity.com/paper/2102.07737/) (2021)
- [PLCMOS -- a data-driven non-intrusive metric for the evaluation of packet loss concealment algorithms](https://mlsanity.com/paper/2305.15127/) (2023)
- [INTERSPEECH 2022 Audio Deep Packet Loss Concealment Challenge](https://mlsanity.com/paper/2204.05222/) (2022)
- [Adversarial Auto-Encoding for Packet Loss Concealment](https://mlsanity.com/paper/2107.03100/) (2021)
- [Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network](https://mlsanity.com/paper/2406.18928/) (2024)
- [tPLCnet: Real-time Deep Packet Loss Concealment in the Time Domain Using a Short Temporal Context](https://mlsanity.com/paper/2204.01300/) (2022)
- [The ICASSP 2024 Audio Deep Packet Loss Concealment Challenge](https://mlsanity.com/paper/2402.16927/) (2024)
- [Improving performance of real-time full-band blind packet-loss concealment with predictive network](https://mlsanity.com/paper/2211.04071/) (2022)

## Abstract (arXiv)

Packet loss concealment (PLC) reconstructs audio packets that are missing at the receiver, usually with a trained model whose parameters remain fixed at deployment time. This treats the PLC model as static, even though each call or recording exposes signal-specific information through the packets that did arrive. We present TTT-PLC, a self-supervised test-time tuning framework that adapts existing PLC models using only those received packets. The method creates supervision by synthetically masking portions of the available signal, training the model to conceal them with its native PLC objective, and then using the adapted model to reconstruct the true packet losses. No clean reference signal, external adaptation data, or architectural modification is required. We study TTT-PLC in two deployment settings. In the non-causal setting, the received file is available before reconstruction, allowing repeated self-supervised adaptation passes and providing a per-file adaptation ceiling. In the causal setting, audio is streamed without revising emitted samples; adaptation is performed only on completed past blocks, and updated parameters affect only future audio. We instantiate the framework on two public PLC backbones, FRN, a recurrent full-band speech PLC model, and PARCnet, a hybrid autoregressive-neural model for networked music. Across these settings, the results show that pretrained PLC systems do not need to be treated as fixed at inference time, the still-observed portions of a lossy signal can provide an effective training signal for improving concealment on that same signal.