# Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrograms

arXiv: https://arxiv.org/abs/2304.02714 · HTML: https://mlsanity.com/paper/2304.02714/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 73 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks](https://mlsanity.com/paper/1810.10863/) (2018)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection](https://mlsanity.com/paper/2103.05094/) (2021)
- [SPA-GAN: Spatial Attention GAN for Image-to-Image Translation](https://mlsanity.com/paper/1908.06616/) (2019)
- [StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding](https://mlsanity.com/paper/2012.08687/) (2020)
- [Reflections on Shannon Information: In search of a natural information-entropy for images](https://mlsanity.com/paper/1609.01117/) (2016)
- [Quality-aware Unpaired Image-to-Image Translation](https://mlsanity.com/paper/1903.06399/) (2019)
- [CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection](https://mlsanity.com/paper/2012.00287/) (2020)
- [Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours](https://mlsanity.com/paper/2005.08894/) (2020)

## Built on by (most cited first, 2 of 2)

- [The Effects of Signal-to-Noise Ratio on Generative Adversarial Networks Applied to Marine Bioacoustic Data](https://mlsanity.com/paper/2312.14806/) (2023)
- [Advancing Marine Bioacoustics with Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection](https://mlsanity.com/paper/2511.21872/) (2025)

## Abstract (arXiv)

Whistle contour extraction aims to derive animal whistles from time-frequency spectrograms as polylines. For toothed whales, whistle extraction results can serve as the basis for analyzing animal abundance, species identity, and social activities. During the last few decades, as long-term recording systems have become affordable, automated whistle extraction algorithms were proposed to process large volumes of recording data. Recently, a deep learning-based method demonstrated superior performance in extracting whistles under varying noise conditions. However, training such networks requires a large amount of labor-intensive annotation, which is not available for many species. To overcome this limitation, we present a framework of stage-wise generative adversarial networks (GANs), which compile new whistle data suitable for deep model training via three stages: generation of background noise in the spectrogram, generation of whistle contours, and generation of whistle signals. By separating the generation of different components in the samples, our framework composes visually promising whistle data and labels even when few expert annotated data are available. Regardless of the amount of human-annotated data, the proposed data augmentation framework leads to a consistent improvement in performance of the whistle extraction model, with a maximum increase of 1.69 in the whistle extraction mean F1-score. Our stage-wise GAN also surpasses one single GAN in improving whistle extraction models with augmented data. The data and code will be available at https://github.com/Paul-LiPu/CompositeGANWhistleAugment.