相关论文: Improving Speaker-independent Speech Emotion Recog…

Unsupervised domain adaptation~(UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. Previous UDA methods assume that the source and target domains share…

Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen…

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial…

Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned…

Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…

In the settings of conventional domain adaptation, categories of the source dataset are from the same domain (or domains for multi-source domain adaptation), which is not always true in reality. In this paper, we propose…

Test-time domain adaption (TTDA) for semantic segmentation aims to adapt a segmentation model trained on a source domain to a target domain for inference on-the-fly, where both efficiency and effectiveness are critical. However, existing…

We propose two methods to make unsupervised domain adaptation (UDA) more parameter efficient using adapters, small bottleneck layers interspersed with every layer of the large-scale pre-trained language model (PLM). The first method…

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature…

Adversarial adaptation models have demonstrated significant progress towards transferring knowledge from a labeled source dataset to an unlabeled target dataset. Partial domain adaptation (PDA) investigates the scenarios in which the source…

Domain adaptation refers to the learning scenario that a model learned from the source data is applied on the target data which have the same categories but different distribution. While it has been widely applied, the distribution…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

Deep learning models excel at many tasks but rely on the assumption that training and test data follow the same distribution. This assumption often does not hold in real-world speech systems, where distribution shifts are common due to…

Domain adaptation aims to mitigate performance degradation caused by distribution shifts between a labeled source domain and an unlabeled or sparsely labeled target domain. Most existing approaches estimate domain discrepancy either in…

Source-Free Domain Adaptation (SFDA) enables domain adaptation for semantic segmentation of Remote Sensing Images (RSIs) using only a well-trained source model and unlabeled target domain data. However, the lack of ground-truth labels in…

Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…

In this work, we present Con$^{2}$DA, a simple framework that extends recent advances in semi-supervised learning to the semi-supervised domain adaptation (SSDA) problem. Our framework generates pairs of associated samples by performing…

When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…

Semi-supervised heterogeneous domain adaptation (SHDA) addresses learning across domains with distinct feature representations and distributions, where source samples are labeled while most target samples are unlabeled, with only a small…

We present a Multi-Window Data Augmentation (MWA-SER) approach for speech emotion recognition. MWA-SER is a unimodal approach that focuses on two key concepts; designing the speech augmentation method and building the deep learning model to…