# Addressing Feature Imbalance in Sound Source Separation

arXiv: https://arxiv.org/abs/2309.05287 · HTML: https://mlsanity.com/paper/2309.05287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 14 of 14)

- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [M2m: Imbalanced Classification via Major-to-minor Translation](https://mlsanity.com/paper/2004.00431/) (2020)
- [Learning from Failure: Training Debiased Classifier from Biased Classifier](https://mlsanity.com/paper/2007.02561/) (2020)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Automatic Shortcut Removal for Self-Supervised Representation Learning](https://mlsanity.com/paper/2002.08822/) (2020)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [The Cone of Silence: Speech Separation by Localization](https://mlsanity.com/paper/2010.06007/) (2020)
- [WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks](https://mlsanity.com/paper/1809.10288/) (2018)
- [Spatial Loss for Unsupervised Multi-channel Source Separation](https://mlsanity.com/paper/2204.00210/) (2022)

## Abstract (arXiv)

Neural networks often suffer from a feature preference problem, where they tend to overly rely on specific features to solve a task while disregarding other features, even if those neglected features are essential for the task. Feature preference problems have primarily been investigated in classification task. However, we observe that feature preference occurs in high-dimensional regression task, specifically, source separation. To mitigate feature preference in source separation, we propose FEAture BAlancing by Suppressing Easy feature (FEABASE). This approach enables efficient data utilization by learning hidden information about the neglected feature. We evaluate our method in a multi-channel source separation task, where feature preference between spatial feature and timbre feature appears.