# Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss

arXiv: https://arxiv.org/abs/2606.29901 · HTML: https://mlsanity.com/paper/2606.29901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks](https://mlsanity.com/paper/2306.04186/) (2023)
- [Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection](https://mlsanity.com/paper/2203.15296/) (2022)
- [Fine-tune the pretrained ATST model for sound event detection](https://mlsanity.com/paper/2309.08153/) (2023)
- [ATST: Audio Representation Learning with Teacher-Student Transformer](https://mlsanity.com/paper/2204.12076/) (2022)
- [Threshold Independent Evaluation of Sound Event Detection Scores](https://mlsanity.com/paper/2201.13148/) (2022)
- [AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer](https://mlsanity.com/paper/2303.03689/) (2023)
- [Sound Event Bounding Boxes](https://mlsanity.com/paper/2406.04212/) (2024)
- [MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection](https://mlsanity.com/paper/2408.08673/) (2024)
- [Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection](https://mlsanity.com/paper/2409.17656/) (2024)
- [RCT: Random Consistency Training for Semi-supervised Sound Event Detection](https://mlsanity.com/paper/2110.11144/) (2021)

## Abstract (arXiv)

Sound event detection (SED) is a core module for acoustic environmental analysis, yet its performance is often limited by scarce labeled data. Recent systems leverage large pretrained audio foundation models, but effective fine-tuning remains challenging because labeled data are limited while unlabeled data are abundant. A previous work, ATST-SED, addressed this problem with a pseudo-label based semi-supervised fine-tuning framework. In this work, we further improve the framework by adopting an embedding-level self-supervised contrastive loss inspired by ATST-Frame pretraining. This contrastive objective better exploits unlabeled data during fine-tuning. One challenge is that mixup serves different roles in the two objectives: pseudo-label learning uses composition mixup, while contrastive learning treats mixup as a perturbation. To resolve this mismatch, we propose conditional mixup, which combines composition mixup and perturbation mixup in one semi-supervised framework and defines the corresponding embedding-level contrastive losses. The resulting model achieves 0.645 PSDS1 and 0.822 PSDS2 on the DESED validation set, establishing a new state of the art.