# Formula-Supervised Sound Event Detection: Pre-Training Without Real Data

arXiv: https://arxiv.org/abs/2504.04428 · HTML: https://mlsanity.com/paper/2504.04428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Builds on (most cited first, 23 of 23)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [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)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Pre-training without Natural Images](https://mlsanity.com/paper/2101.08515/) (2021)
- [The Benefit Of Temporally-Strong Labels In Audio Event Classification](https://mlsanity.com/paper/2105.07031/) (2021)
- [Sound Event Detection: A Tutorial](https://mlsanity.com/paper/2107.05463/) (2021)
- [Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection](https://mlsanity.com/paper/1702.06286/) (2017)
- [Can Vision Transformers Learn without Natural Images?](https://mlsanity.com/paper/2103.13023/) (2021)
- [A Framework for the Robust Evaluation of Sound Event Detection](https://mlsanity.com/paper/1910.08440/) (2019)
- [Improving Fractal Pre-training](https://mlsanity.com/paper/2110.03091/) (2021)
- [Pre-training Vision Transformers with Formula-driven Supervised Learning](https://mlsanity.com/paper/2206.09132/) (2022)
- [Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenes](https://mlsanity.com/paper/1711.01369/) (2017)
- [Large-scale weakly supervised audio classification using gated convolutional neural network](https://mlsanity.com/paper/1710.00343/) (2017)
- [Fine-tune the pretrained ATST model for sound event detection](https://mlsanity.com/paper/2309.08153/) (2023)
- [Scaling Backwards: Minimal Synthetic Pre-training?](https://mlsanity.com/paper/2408.00677/) (2024)
- [Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments](https://mlsanity.com/paper/1807.10501/) (2018)
- [AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer](https://mlsanity.com/paper/2303.03689/) (2023)
- [Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-supervised Sound Event Detection](https://mlsanity.com/paper/2103.06581/) (2021)
- [SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning](https://mlsanity.com/paper/2309.17083/) (2023)
- [Semi-supervsied Learning-based Sound Event Detection using Freuqency Dynamic Convolution with Large Kernel Attention for DCASE Challenge 2023 Task 4](https://mlsanity.com/paper/2306.06461/) (2023)
- [hear-your-action: human action recognition by ultrasound active sensing](https://mlsanity.com/paper/2309.08087/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametrically synthesized through formula-driven methods. Specifically, we outline detailed procedures and evaluate their effectiveness for sound event detection (SED). The SED task, which involves estimating the types and timings of sound events, is particularly challenged by the difficulty of acquiring a sufficient quantity of accurately labeled training data. Moreover, it is well known that manually annotated labels often contain noises and are significantly influenced by the subjective judgment of annotators. To address these challenges, we propose a novel pre-training method that utilizes a synthetic dataset, Formula-SED, where acoustic data are generated solely based on mathematical formulas. The proposed method enables large-scale pre-training by using the synthesis parameters applied at each time step as ground truth labels, thereby eliminating label noise and bias. We demonstrate that large-scale pre-training with Formula-SED significantly enhances model accuracy and accelerates training, as evidenced by our results in the DESED dataset used for DCASE2023 Challenge Task 4. The project page is at https://yutoshibata07.github.io/Formula-SED/