# Affinity Mixup for Weakly Supervised Sound Event Detection

arXiv: https://arxiv.org/abs/2106.11233 · HTML: https://mlsanity.com/paper/2106.11233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Optimization of Graph Neural Networks with Natural Gradient Descent](https://mlsanity.com/paper/2008.09624/) (2020)
- [Towards duration robust weakly supervised sound event detection](https://mlsanity.com/paper/2101.07687/) (2021)
- [Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection](https://mlsanity.com/paper/1905.10091/) (2019)
- [Duration robust weakly supervised sound event detection](https://mlsanity.com/paper/1904.03841/) (2019)

## Abstract (arXiv)

The weakly supervised sound event detection problem is the task of predicting the presence of sound events and their corresponding starting and ending points in a weakly labeled dataset. A weak dataset associates each training sample (a short recording) to one or more present sources. Networks that solely rely on convolutional and recurrent layers cannot directly relate multiple frames in a recording. Motivated by attention and graph neural networks, we introduce the concept of an affinity mixup to incorporate time-level similarities and make a connection between frames. This regularization technique mixes up features in different layers using an adaptive affinity matrix. Our proposed affinity mixup network improves over state-of-the-art techniques event-F1 scores by 8.2%.