# Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation

arXiv: https://arxiv.org/abs/2311.12199 · HTML: https://mlsanity.com/paper/2311.12199/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 29 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks](https://mlsanity.com/paper/1703.06284/) (2017)
- [Wavesplit: End-to-End Speech Separation by Speaker Clustering](https://mlsanity.com/paper/2002.08933/) (2020)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [Sudo rm -rf: Efficient Networks for Universal Audio Source Separation](https://mlsanity.com/paper/2007.06833/) (2020)
- [Voice Separation with an Unknown Number of Multiple Speakers](https://mlsanity.com/paper/2003.01531/) (2020)
- [Asteroid: the PyTorch-based audio source separation toolkit for researchers](https://mlsanity.com/paper/2005.04132/) (2020)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement](https://mlsanity.com/paper/2104.13002/) (2021)
- [SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation](https://mlsanity.com/paper/2201.10800/) (2022)
- [Probabilistic Permutation Invariant Training for Speech Separation](https://mlsanity.com/paper/1908.01768/) (2019)
- [Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation](https://mlsanity.com/paper/2103.00819/) (2021)
- [TransMask: A Compact and Fast Speech Separation Model Based on Transformer](https://mlsanity.com/paper/2102.09978/) (2021)
- [Interrupted and cascaded permutation invariant training for speech separation](https://mlsanity.com/paper/1910.12706/) (2019)
- [Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm](https://mlsanity.com/paper/2010.11871/) (2020)
- [Latent Iterative Refinement for Modular Source Separation](https://mlsanity.com/paper/2211.11917/) (2022)
- [Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training](https://mlsanity.com/paper/2010.15366/) (2020)
- [BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement](https://mlsanity.com/paper/2111.09372/) (2021)
- [Single-channel speech separation using Soft-minimum Permutation Invariant Training](https://mlsanity.com/paper/2111.08635/) (2021)

## Abstract (arXiv)

In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. To address this issue, we propose a novel training strategy, dynamic sample dropout (DSD), which considers previous best label assignments and evaluation metrics to exclude the samples that may negatively impact the learned label assignments during training. Additionally, we include layer-wise optimization (LO) to improve the performance by solving layer-decoupling. Our experiments showed that combining DSD and LO outperforms the baseline and solves excessive label assignment switching and layer-decoupling issues. The proposed DSD and LO approach is easy to implement, requires no extra training sets or steps, and shows generality to various speech separation tasks.