# Improving Bird Classification with Unsupervised Sound Separation

arXiv: https://arxiv.org/abs/2110.03209 · HTML: https://mlsanity.com/paper/2110.03209/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2021.

## Built on by (most cited first, 25 of 25)

- [BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics](https://mlsanity.com/paper/2403.10380/) (2024)
- [Perch 2.0: The Bittern Lesson for Bioacoustics](https://mlsanity.com/paper/2508.04665/) (2025)
- [Out-of-Domain Robustness via Targeted Augmentations](https://mlsanity.com/paper/2302.11861/) (2023)
- [BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics](https://mlsanity.com/paper/2312.07439/) (2023)
- [Self-Supervised Learning for Few-Shot Bird Sound Classification](https://mlsanity.com/paper/2312.15824/) (2023)
- [Unsupervised classification to improve the quality of a bird song recording dataset](https://mlsanity.com/paper/2302.07560/) (2023)
- [AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring](https://mlsanity.com/paper/2307.06860/) (2023)
- [AudioProtoPNet: An interpretable deep learning model for bird sound classification](https://mlsanity.com/paper/2404.10420/) (2024)
- [Towards Deep Active Learning in Avian Bioacoustics](https://mlsanity.com/paper/2406.18621/) (2024)
- [Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics](https://mlsanity.com/paper/2404.16436/) (2024)
- [Robust detection of overlapping bioacoustic sound events](https://mlsanity.com/paper/2503.02389/) (2025)
- [Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data](https://mlsanity.com/paper/2301.11981/) (2023)
- [Multi-scale clustering and source separation of InSight mission seismic data](https://mlsanity.com/paper/2305.16189/) (2023)
- [Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers](https://mlsanity.com/paper/2308.07121/) (2023)
- [Synthetic data enables context-aware bioacoustic sound event detection](https://mlsanity.com/paper/2503.00296/) (2025)
- [MetaPerch: Learning from metadata for bioacoustics foundation models](https://mlsanity.com/paper/2607.14072/) (2026)
- [Uncertainty Calibration of Multi-Label Bird Sound Classifiers](https://mlsanity.com/paper/2511.08261/) (2025)
- [Correlation Clustering of Bird Sounds](https://mlsanity.com/paper/2306.09906/) (2023)
- [Transfer Learning with Semi-Supervised Dataset Annotation for Birdcall Classification](https://mlsanity.com/paper/2306.16760/) (2023)
- [An empirical study of automatic wildlife detection using drone thermal imaging and object detection](https://mlsanity.com/paper/2310.11257/) (2023)
- [Unsupervised outlier detection to improve bird audio dataset labels](https://mlsanity.com/paper/2504.18650/) (2025)
- [Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification](https://mlsanity.com/paper/2507.13727/) (2025)
- [Improving Bird Classification with Primary Color Additives](https://mlsanity.com/paper/2507.18334/) (2025)
- [Multi-Representation Attention Framework for Underwater Bioacoustic Denoising and Recognition](https://mlsanity.com/paper/2510.26838/) (2025)
- [Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026](https://mlsanity.com/paper/2607.14474/) (2026)

## Abstract (arXiv)

This paper addresses the problem of species classification in bird song recordings. The massive amount of available field recordings of birds presents an opportunity to use machine learning to automatically track bird populations. However, it also poses a problem: such field recordings typically contain significant environmental noise and overlapping vocalizations that interfere with classification. The widely available training datasets for species identification also typically leave background species unlabeled. This leads classifiers to ignore vocalizations with a low signal-to-noise ratio. However, recent advances in unsupervised sound separation, such as mixture invariant training (MixIT), enable high quality separation of bird songs to be learned from such noisy recordings. In this paper, we demonstrate improved separation quality when training a MixIT model specifically for birdsong data, outperforming a general audio separation model by over 5 dB in SI-SNR improvement of reconstructed mixtures. We also demonstrate precision improvements with a downstream multi-species bird classifier across three independent datasets. The best classifier performance is achieved by taking the maximum model activations over the separated channels and original audio. Finally, we document additional classifier improvements, including taxonomic classification, augmentation by random low-pass filters, and additional channel normalization.