# Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection

arXiv: https://arxiv.org/abs/1905.10091 · HTML: https://mlsanity.com/paper/1905.10091/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 5 of 5)

- [Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection](https://mlsanity.com/paper/2110.02011/) (2021)
- [Improving Weakly Supervised Sound Event Detection with Causal Intervention](https://mlsanity.com/paper/2303.05678/) (2023)
- [Affinity Mixup for Weakly Supervised Sound Event Detection](https://mlsanity.com/paper/2106.11233/) (2021)
- [A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4](https://mlsanity.com/paper/2210.09529/) (2022)
- [Leveraging Language Model Capabilities for Sound Event Detection](https://mlsanity.com/paper/2308.11530/) (2023)

## Abstract (arXiv)

In this paper, a special decision surface for the weakly-supervised sound event detection (SED) and a disentangled feature (DF) for the multi-label problem in polyphonic SED are proposed. We approach SED as a multiple instance learning (MIL) problem and utilize a neural network framework with a pooling module to solve it. General MIL approaches include two kinds: the instance-level approaches and embedding-level approaches. We present a method of generating instance-level probabilities for the embedding level approaches which tend to perform better than the instance-level approaches in terms of bag-level classification but can not provide instance-level probabilities in current approaches. Moreover, we further propose a specialized decision surface (SDS) for the embedding-level attention pooling. We analyze and explained why an embedding-level attention module with SDS is better than other typical pooling modules from the perspective of the high-level feature space. As for the problem of the unbalanced dataset and the co-occurrence of multiple categories in the polyphonic event detection task, we propose a DF to reduce interference among categories, which optimizes the high-level feature space by disentangling it based on class-wise identifiable information and obtaining multiple different subspaces. Experiments on the dataset of DCASE 2018 Task 4 show that the proposed SDS and DF significantly improve the detection performance of the embedding-level MIL approach with an attention pooling module and outperform the first place system in the challenge by 6.6 percentage points.