# Mixup-breakdown: a consistency training method for improving generalization of speech separation models

arXiv: https://arxiv.org/abs/1910.13253 · HTML: https://mlsanity.com/paper/1910.13253/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation](https://mlsanity.com/paper/2103.00819/) (2021)
- [Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation](https://mlsanity.com/paper/2106.07843/) (2021)
- [Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks](https://mlsanity.com/paper/2101.05014/) (2021)
- [MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training](https://mlsanity.com/paper/2202.03875/) (2022)
- [MixupE: Understanding and Improving Mixup from Directional Derivative Perspective](https://mlsanity.com/paper/2212.13381/) (2022)
- [A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References](https://mlsanity.com/paper/2508.14623/) (2025)
- [Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect](https://mlsanity.com/paper/2103.01461/) (2021)
- [Revisiting Interpolation Augmentation for Speech-to-Text Generation](https://mlsanity.com/paper/2406.15846/) (2024)

## Abstract (arXiv)

Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an easy-to-implement yet effective consistency based semi-supervised learning (SSL) approach, namely Mixup-Breakdown training (MBT). It learns a teacher model to "breakdown" unlabeled inputs, and the estimated separations are interpolated to produce more useful pseudo "mixup" input-output pairs, on which the consistency regularization could apply for learning a student model. In our experiment, we evaluate MBT under various conditions with ascending degrees of mismatch, including unseen interfering speech, noise, and music, and compare MBT's generalization capability against state-of-the-art supervised learning and SSL approaches. The result indicates that MBT significantly outperforms several strong baselines with up to 13.77% relative SI-SNRi improvement. Moreover, MBT only adds negligible computational overhead to standard training schemes.