# Towards duration robust weakly supervised sound event detection

arXiv: https://arxiv.org/abs/2101.07687 · HTML: https://mlsanity.com/paper/2101.07687/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2021.

## Built on by (most cited first, 11 of 11)

- [You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection](https://mlsanity.com/paper/2109.00962/) (2021)
- [Voice activity detection in the wild: A data-driven approach using teacher-student training](https://mlsanity.com/paper/2105.04065/) (2021)
- [Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection](https://mlsanity.com/paper/2205.11738/) (2022)
- [Improving Weakly Supervised Sound Event Detection with Causal Intervention](https://mlsanity.com/paper/2303.05678/) (2023)
- [Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity](https://mlsanity.com/paper/2210.06354/) (2022)
- [Streaming Anchor Loss: Augmenting Supervision with Temporal Significance](https://mlsanity.com/paper/2310.05886/) (2023)
- [Affinity Mixup for Weakly Supervised Sound Event Detection](https://mlsanity.com/paper/2106.11233/) (2021)
- [VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild](https://mlsanity.com/paper/2303.06048/) (2023)
- [MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection](https://mlsanity.com/paper/2409.06196/) (2024)
- [WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?](https://mlsanity.com/paper/2602.01850/) (2026)
- [Shared Representation Learning for Reference-Guided Targeted Sound Detection](https://mlsanity.com/paper/2603.17025/) (2026)

## Abstract (arXiv)

Sound event detection (SED) is the task of tagging the absence or presence of audio events and their corresponding interval within a given audio clip. While SED can be done using supervised machine learning, where training data is fully labeled with access to per event timestamps and duration, our work focuses on weakly-supervised sound event detection (WSSED), where prior knowledge about an event's duration is unavailable. Recent research within the field focuses on improving segment- and event-level localization performance for specific datasets regarding specific evaluation metrics. Specifically, well-performing event-level localization requires fully labeled development subsets to obtain event duration estimates, which significantly benefits localization performance. Moreover, well-performing segment-level localization models output predictions at a coarse-scale (e.g., 1 second), hindering their deployment on datasets containing very short events (< 1 second). This work proposes a duration robust CRNN (CDur) framework, which aims to achieve competitive performance in terms of segment- and event-level localization. This paper proposes a new post-processing strategy named "Triple Threshold" and investigates two data augmentation methods along with a label smoothing method within the scope of WSSED. Evaluation of our model is done on the DCASE2017 and 2018 Task 4 datasets, and URBAN-SED. Our model outperforms other approaches on the DCASE2018 and URBAN-SED datasets without requiring prior duration knowledge. In particular, our model is capable of similar performance to strongly-labeled supervised models on the URBAN-SED dataset. Lastly, ablation experiments to reveal that without post-processing, our model's localization performance drop is significantly lower compared with other approaches.