Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization

• URL: http://arxiv.org/abs/2106.10127v1
• Date: Fri, 18 Jun 2021 13:34:36 GMT
• Title: Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization
• Authors: Disong Wang, Liqun Deng, Yu Ting Yeung, Xiao Chen, Xunying Liu, Helen Meng
• Abstract summary: This paper makes a first attempt to formulate cross-domain Dysarthric speech detection (DSD) as an unsupervised domain adaptation problem. We propose a multi-task learning strategy, including dysarthria presence classification (DPC), domain adversarial training ( DAT) and mutual information minimization (MIM) Experiments show that the incorporation of UDA attains absolute increases of 22.2% and 20.0% respectively in utterance-level weighted average recall and speaker-level accuracy.
• Score: 52.82138296332476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target domains respectively, but the two domains may differ in terms of speech stimuli, disease etiology, etc. It is hard to acquire labelled data in the target domain, due to high costs of annotating sizeable datasets. This paper makes a first attempt to formulate cross-domain DSD as an unsupervised domain adaptation (UDA) problem. We use labelled source-domain data and unlabelled target-domain data, and propose a multi-task learning strategy, including dysarthria presence classification (DPC), domain adversarial training (DAT) and mutual information minimization (MIM), which aim to learn dysarthria-discriminative and domain-invariant biomarker embeddings. Specifically, DPC helps biomarker embeddings capture critical indicators of dysarthria; DAT forces biomarker embeddings to be indistinguishable in source and target domains; and MIM further reduces the correlation between biomarker embeddings and domain-related cues. By treating the UASPEECH and TORGO corpora respectively as the source and target domains, experiments show that the incorporation of UDA attains absolute increases of 22.2% and 20.0% respectively in utterance-level weighted average recall and speaker-level accuracy.

Related papers

• Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning [46.248404274124546]
  Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models. This paper proposes a simple yet potent contrastive learning framework for UDA to narrow the inter-domain gap between labelled source and unlabelled target distribution.
  arXiv  Detail & Related papers  (2024-02-23T10:01:22Z)
• Subject-Based Domain Adaptation for Facial Expression Recognition [51.10374151948157]
  Adapting a deep learning model to a specific target individual is a challenging facial expression recognition task. This paper introduces a new MSDA method for subject-based domain adaptation in FER. It efficiently leverages information from multiple source subjects to adapt a deep FER model to a single target individual.
  arXiv  Detail & Related papers  (2023-12-09T18:40:37Z)
• IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation [46.6002506426648]
  Unsupervised domain adaptation (UDA) is the dominant approach to solve this problem. We propose semi-supervised domain adaptation (SSDA) to overcome this limitation. We propose a novel framework that incorporates both Inter and Intra Domain Mixing (IIDM), where inter-domain mixing mitigates the source-target domain gap and intra-domain mixing enriches the available target domain information.
  arXiv  Detail & Related papers  (2023-08-30T08:44:21Z)
• Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning [57.43322536718131]
  We present a two-stage source-free domain adaptation (SFDA) framework for medical image segmentation. In the prototype-anchored feature alignment stage, we first utilize the weights of the pre-trained pixel-wise classifier as source prototypes. Then, we introduce the bi-directional transport to align the target features with class prototypes by minimizing its expected cost.
  arXiv  Detail & Related papers  (2023-07-19T06:07:12Z)
• Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation [2.734665397040629]
  Multi-source Unsupervised Domain Adaptation transfers knowledge from multiple source domains with labeled data to an unlabeled target domain. The distribution discrepancy between different domains and the noisy pseudo-labels in the target domain both lead to performance bottlenecks. We propose an approach that integrates Attention-driven Domain fusion and Noise-Tolerant learning (ADNT) to address the two issues mentioned above.
  arXiv  Detail & Related papers  (2022-08-05T01:08:41Z)
• ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training [34.017031149886556]
  Unsupervised domain adaptation (UDA) has been vastly explored to alleviate domain shifts between source and target domains. We propose to exploit both labeled source and target domain data, in addition to unlabeled target data in a unified manner. We present a novel asymmetric co-training (ACT) framework to integrate these subsets and avoid the domination of the source domain data.
  arXiv  Detail & Related papers  (2022-06-05T23:48:00Z)
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID [58.46907388691056]
  We argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task. We propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks.
  arXiv  Detail & Related papers  (2021-08-05T07:19:46Z)
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation [76.41664929948607]
  Semi-supervised domain adaptation (SSDA) methods have demonstrated great potential in large-scale image classification tasks. We present a novel and effective method to tackle this problem by using effective inter-domain and intra-domain semantic information propagation. Our source code and pre-trained models will be released soon.
  arXiv  Detail & Related papers  (2020-12-04T14:28:19Z)
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation [67.83872616307008]
  Unversarial Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. In this paper, we propose a novel Adrial Dual Distincts Network (AD$2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment.
  arXiv  Detail & Related papers  (2020-08-27T01:29:10Z)

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.