Self-Train Before You Transcribe

• URL: http://arxiv.org/abs/2406.12937v1
• Date: Mon, 17 Jun 2024 09:21:00 GMT
• Title: Self-Train Before You Transcribe
• Authors: Robert Flynn, Anton Ragni,
• Abstract summary: We investigate the benefit of performing noisy student teacher training on recordings in the test set as a test-time adaptation approach. A range of in-domain and out-of-domain datasets are used for experiments demonstrating large relative gains of up to 32.2%.
• Score: 3.17829719401032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the adaptation of models under such domain shifts. However, self-training typically requires a collection of unlabelled target domain data. For settings where this is not practical, we investigate the benefit of performing noisy student teacher training on recordings in the test set as a test-time adaptation approach. Similarly to the dynamic evaluation approach in language modelling, this enables the transfer of information across utterance boundaries and functions as a method of domain adaptation. A range of in-domain and out-of-domain datasets are used for experiments demonstrating large relative gains of up to 32.2%. Interestingly, our method showed larger gains than the typical self-training setup that utilises separate adaptation data.

Related papers

• Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition [1.2878987353423252]
  Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR) We introduce the Stratified Domain Adaptation (StrDA) approach, which examines the gradual escalation of the domain gap for the learning process. We propose a novel method for employing domain discriminators to estimate the out-of-distribution and domain discriminative levels of data samples.
  arXiv  Detail & Related papers  (2024-10-13T16:40:48Z)
• 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)
• Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition [36.83842373791537]
  Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model. Previous studies focus on single domain adaptation, which neglects a more practical scenario where training data are collected from multiple acoustic domains. Three novel adaptation methods are proposed to further promote adaptation performance across multiple acoustic domains.
  arXiv  Detail & Related papers  (2022-11-17T22:11:25Z)
• RAIS: Robust and Accurate Interactive Segmentation via Continual Learning [16.382862088005087]
  We propose RAIS, a robust and accurate architecture for interactive segmentation with continuous learning. For efficient learning on the test set, we propose a novel optimization strategy to update global and local parameters. Our method also shows its robustness in the datasets of remote sensing and medical imaging.
  arXiv  Detail & Related papers  (2022-10-20T03:05:44Z)
• One-Class Knowledge Distillation for Face Presentation Attack Detection [53.30584138746973]
  This paper introduces a teacher-student framework to improve the cross-domain performance of face PAD with one-class domain adaptation. Student networks are trained to mimic the teacher network and learn similar representations for genuine face samples of the target domain. In the test phase, the similarity score between the representations of the teacher and student networks is used to distinguish attacks from genuine ones.
  arXiv  Detail & Related papers  (2022-05-08T06:20:59Z)
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data [64.91713686654805]
  The Visual Domain Adaptation (VisDA) 2021 competition tests models' ability to adapt to novel test distributions. We will evaluate adaptation to novel viewpoints, backgrounds, modalities and degradation in quality. Performance will be measured using a rigorous protocol, comparing to state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2021-07-23T03:21:51Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization [69.12982544509427]
  S-temporal action localization is an important problem in computer vision. We propose an end-to-end unsupervised domain adaptation algorithm. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately or jointly.
  arXiv  Detail & Related papers  (2020-10-19T04:25:10Z)
• A Brief Review of Domain Adaptation [1.2043574473965317]
  This paper focuses on unsupervised domain adaptation, where the labels are only available in the source domain. It presents some successful shallow and deep domain adaptation approaches that aim to deal with domain adaptation problems.
  arXiv  Detail & Related papers  (2020-10-07T07:05:32Z)
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift [109.87561509436016]
  A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts. We introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains.
  arXiv  Detail & Related papers  (2020-07-06T17:59:30Z)
• Don't Stop Pretraining: Adapt Language Models to Domains and Tasks [81.99843216550306]
  We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks. A second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains. Adapting to the task's unlabeled data (task-adaptive pretraining) improves performance even after domain-adaptive pretraining.
  arXiv  Detail & Related papers  (2020-04-23T04:21:19Z)

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.