Mixup-breakdown: a consistency training method for improving generalization of speech separation models
arXiv:1910.13253
Abstract
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.
Accepted in a Lesson session in ICASSP2020
References in corpus (11)
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Temporal Ensembling for Semi-Supervised Learning
- Interpolation Consistency Training for Semi-Supervised Learning
- Data Augmentation Generative Adversarial Networks
- Semi-Supervised Learning with Ladder Networks
- Deep attractor network for single-microphone speaker separation
- SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules
- Speaker-independent Speech Separation with Deep Attractor Network
- End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction
- Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures
- Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering