mlsanityData to 14 Oct 2026

Progressive Learning for Stabilizing Label Selection in Speech Separation with Mapping-based Method

arXiv 2110.10593 ↗First posted 20 Oct 2021cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based) has been inadequately studied. We investigate the use of the mapping-based method in the time domain and show that it can perform better on a large training set than the masking-based method. We also investigate the frequent label-switching problem in permutation invariant training (PIT), which results in suboptimal training because the labels selected by PIT differ across training epochs. Our experiment results showed that PIT works well in a shallow separation model, and the label switching occurs for a deeper model. We inferred that layer decoupling may be the reason for the frequent label switching. Therefore, we propose a training strategy based on progressive learning. This approach significantly reduced inconsistent label assignment without added computational complexity or training corpus. By combining this training strategy with the mapping-based method, we significantly improved the separation performance compared to the baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 20 Oct 2021.

Builds on

18 of 26 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018SDR - half-baked or well done?cited by 423
  3. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  4. 2015Deep clustering: Discriminative embeddings for segmentation and separationcited by 212
  5. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 191
  6. 2020Attention is All You Need in Speech Separationcited by 185
  7. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  8. 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 155
  9. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  10. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 75
  11. 2020Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separationcited by 68
  12. 2020Voice Separation with an Unknown Number of Multiple Speakerscited by 46
6 more
  1. 2020Asteroid: the PyTorch-based audio source separation toolkit for researcherscited by 45
  2. 2019Probabilistic Permutation Invariant Training for Speech Separationcited by 12
  3. 2021Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separationcited by 10
  4. 2021TransMask: A Compact and Fast Speech Separation Model Based on Transformercited by 9
  5. 2019Interrupted and cascaded permutation invariant training for speech separationcited by 8
  6. 2020Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-trainingcited by 6

Built on by

Not cited yet.