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

• URL: http://arxiv.org/abs/2311.12199v1
• Date: Mon, 20 Nov 2023 21:37:38 GMT
• Title: Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation
• Authors: Chenyang Gao, Yue Gu, Ivan Marsic
• Abstract summary: In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. 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.
• Score: 8.489574755691613
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Online Feature Updates Improve Online (Generalized) Label Shift Adaptation [54.3888105557787]
  This paper addresses the prevalent issue of label shift in an online setting with missing labels. We explore the untapped potential of enhancing feature representations using unlabeled data at test-time. Our method, Online Label Shift adaptation with Online Feature Updates (OLS-OFU), leverages self-supervised learning to refine the feature extraction process.
  arXiv  Detail & Related papers  (2024-02-05T22:03:25Z)
• Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement [9.69089112870202]
  We propose an auxiliary pseudo-label refinement network (PRN) for online refining of the pseudo labels and also localizing the pixels whose predicted labels are likely to be noisy. We evaluate our approach on benchmark datasets with three different domain shifts, and our approach consistently performs significantly better than the previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-25T20:31:07Z)
• Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification [0.0]
  This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-25T10:10:48Z)
• Single-channel speech separation using Soft-minimum Permutation Invariant Training [60.99112031408449]
  A long-lasting problem in supervised speech separation is finding the correct label for each separated speech signal. Permutation Invariant Training (PIT) has been shown to be a promising solution in handling the label ambiguity problem. In this work, we propose a probabilistic optimization framework to address the inefficiency of PIT in finding the best output-label assignment.
  arXiv  Detail & Related papers  (2021-11-16T17:25:05Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation [116.48885692054724]
  We propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation. We develop a deep Q-learning model to select both accurate and representative pseudo-labeled instances. Our proposed method is evaluated on several benchmark datasets for SSDA, and demonstrates superior performance to all the comparison methods.
  arXiv  Detail & Related papers  (2020-12-07T03:37:38Z)
• Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training [58.30339239234169]
  We propose to perform self-supervised pre-training to stabilize the label assignment in training the speech separation model. Experiments over several types of self-supervised approaches, several typical speech separation models and two different datasets showed that very good improvements are achievable if a proper self-supervised approach is chosen.
  arXiv  Detail & Related papers  (2020-10-29T06:07:01Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.