Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

• URL: http://arxiv.org/abs/2011.13439v2
• Date: Tue, 16 Feb 2021 17:00:46 GMT
• Title: Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training
• Authors: Sameer Khurana, Niko Moritz, Takaaki Hori, Jonathan Le Roux
• Abstract summary: 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.
• Score: 55.824641135682725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high uncertainties from the training, which leads to substantially improved ASR results compared to ST without filtering, and accelerates the training time due to a reduced training data set. Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD as the target domains show that up to 80% of the performance of a system trained on ground-truth data can be recovered.

Related papers

• Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis [7.88657961743755]
  Unsupervised domain adaptation (UDA) deals with the scenario where labeled data are available in a source domain, and only unlabeled data are available in a target domain. We propose a novel UDA method called Calibrated Adaptive Teacher (CAT), where we propose to calibrate the predictions of the teacher network throughout the self-training process.
  arXiv  Detail & Related papers  (2023-12-05T15:19:29Z)
• Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation [12.080054869408213]
  We develop a generative self-training framework for domain adaptive image translation with continuous value prediction and regression objectives. We evaluate our framework on two cross-scanner/center, inter-subject translation tasks, including tagged-to-cine magnetic resonance (MR) image translation and T1-weighted MR-to-fractional anisotropy translation.
  arXiv  Detail & Related papers  (2023-05-23T23:57:44Z)
• Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer [60.31021888394358]
  Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) We propose a SOurce-free Domain Adaptation framework for image SR (SODA-SR) to address this issue, i.e., adapt a source-trained model to a target domain with only unlabeled target data.
  arXiv  Detail & Related papers  (2023-03-31T03:14:44Z)
• Boosting Cross-Domain Speech Recognition with Self-Supervision [35.01508881708751]
  Cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to mismatch between training and testing distributions. Previous work has shown that self-supervised learning (SSL) or pseudo-labeling (PL) is effective in UDA by exploiting the self-supervisions of unlabeled data. This work presents a systematic UDA framework to fully utilize the unlabeled data with self-supervision in the pre-training and fine-tuning paradigm.
  arXiv  Detail & Related papers  (2022-06-20T14:02:53Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection [6.345037597566315]
  Pseudo-label based self training approaches are a popular method for source-free unsupervised domain adaptation. We propose an uncertainty-aware mean teacher framework which implicitly filters incorrect pseudo-labels during training.
  arXiv  Detail & Related papers  (2021-09-29T18:17:09Z)
• Cycle Self-Training for Domain Adaptation [85.14659717421533]
  Cycle Self-Training (CST) is a principled self-training algorithm that enforces pseudo-labels to generalize across domains. CST recovers target ground truth, while both invariant feature learning and vanilla self-training fail. Empirical results indicate that CST significantly improves over prior state-of-the-arts in standard UDA benchmarks.
  arXiv  Detail & Related papers  (2021-03-05T10:04:25Z)
• Understanding Self-Training for Gradual Domain Adaptation [107.37869221297687]
  We consider gradual domain adaptation, where the goal is to adapt an initial classifier trained on a source domain given only unlabeled data that shifts gradually in distribution towards a target domain. We prove the first non-vacuous upper bound on the error of self-training with gradual shifts, under settings where directly adapting to the target domain can result in unbounded error. The theoretical analysis leads to algorithmic insights, highlighting that regularization and label sharpening are essential even when we have infinite data, and suggesting that self-training works particularly well for shifts with small Wasserstein-infinity distance.
  arXiv  Detail & Related papers  (2020-02-26T08:59:40Z)

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.