# Weakly Labelled AudioSet Tagging with Attention Neural Networks

arXiv: https://arxiv.org/abs/1903.00765 · HTML: https://mlsanity.com/paper/1903.00765/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2019.

## Built on by (most cited first, 17 of 17)

- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Audio Captioning Transformer](https://mlsanity.com/paper/2107.09817/) (2021)
- [Automated Audio Captioning: An Overview of Recent Progress and New Challenges](https://mlsanity.com/paper/2205.05949/) (2022)
- [Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning](https://mlsanity.com/paper/2302.04061/) (2023)
- [Graph Force Learning](https://mlsanity.com/paper/2103.04344/) (2021)
- [Pretrained audio neural networks for Speech emotion recognition in Portuguese](https://mlsanity.com/paper/2210.14716/) (2022)
- [Towards Generating Diverse Audio Captions via Adversarial Training](https://mlsanity.com/paper/2212.02033/) (2022)
- [LEAN: Light and Efficient Audio Classification Network](https://mlsanity.com/paper/2305.12712/) (2023)
- [Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning](https://mlsanity.com/paper/2103.00833/) (2021)
- [Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregation](https://mlsanity.com/paper/2205.14428/) (2022)
- [Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification](https://mlsanity.com/paper/2504.15214/) (2025)
- [Nonparametric Teaching of Attention Learners](https://mlsanity.com/paper/2602.20461/) (2026)
- [Shared Representation Learning for Reference-Guided Targeted Sound Detection](https://mlsanity.com/paper/2603.17025/) (2026)
- [An Analysis of Untrained Deep Reservoir Networks for Audio Surveillance](https://mlsanity.com/paper/2606.22218/) (2026)
- [TCPα: Margin-Controlled Confidence estimation for reliable Music Information Retrieval](https://mlsanity.com/paper/2608.20326/) (2026)

## Abstract (arXiv)

Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We investigate audio tagging on AudioSet, which is a dataset consisting of over 2 million audio clips and 527 classes. AudioSet is weakly labelled, in that only the presence or absence of sound classes is known for each clip, while the onset and offset times are unknown. To address the weakly-labelled audio tagging problem, we propose attention neural networks as a way to attend the most salient parts of an audio clip. We bridge the connection between attention neural networks and multiple instance learning (MIL) methods, and propose decision-level and feature-level attention neural networks for audio tagging. We investigate attention neural networks modeled by different functions, depths and widths. Experiments on AudioSet show that the feature-level attention neural network achieves a state-of-the-art mean average precision (mAP) of 0.369, outperforming the best multiple instance learning (MIL) method of 0.317 and Google's deep neural network baseline of 0.314. In addition, we discover that the audio tagging performance on AudioSet embedding features has a weak correlation with the number of training samples and the quality of labels of each sound class.