# From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning

arXiv: https://arxiv.org/abs/2403.08525 · HTML: https://mlsanity.com/paper/2403.08525/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [The Benefit Of Temporally-Strong Labels In Audio Event Classification](https://mlsanity.com/paper/2105.07031/) (2021)
- [Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization](https://mlsanity.com/paper/1912.04761/) (2019)
- [Few-shot bioacoustic event detection at the DCASE 2022 challenge](https://mlsanity.com/paper/2207.07911/) (2022)
- [The NIGENS General Sound Events Database](https://mlsanity.com/paper/1902.08314/) (2019)
- [Crowdsourcing strong labels for sound event detection](https://mlsanity.com/paper/2107.12089/) (2021)

## Built on by (most cited first, 4 of 4)

- [Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection](https://mlsanity.com/paper/2505.20956/) (2025)
- [The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time](https://mlsanity.com/paper/2502.09363/) (2025)
- [Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning](https://mlsanity.com/paper/2607.13555/) (2026)
- [Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference](https://mlsanity.com/paper/2609.27409/) (2026)

## Abstract (arXiv)

We propose an adaptive change point detection method (A-CPD) for machine guided weak label annotation of audio recording segments. The goal is to maximize the amount of information gained about the temporal activations of the target sounds. For each unlabeled audio recording, we use a prediction model to derive a probability curve used to guide annotation. The prediction model is initially pre-trained on available annotated sound event data with classes that are disjoint from the classes in the unlabeled dataset. The prediction model then gradually adapts to the annotations provided by the annotator in an active learning loop. We derive query segments to guide the weak label annotator towards strong labels, using change point detection on these probabilities. We show that it is possible to derive strong labels of high quality with a limited annotation budget, and show favorable results for A-CPD when compared to two baseline query segment strategies.