中文
相关论文

相关论文: MADI: Inter-domain Matching and Intra-domain Discr…

200 篇论文

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

音频与语音处理 · 电气工程与系统科学 2023-08-01 Han Zhu , Gaofeng Cheng , Jindong Wang , Wenxin Hou , Pengyuan Zhang , Yonghong Yan

Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy. However, most of the studies were based on direct adaptation from the…

计算机视觉与模式识别 · 计算机科学 2022-02-22 Qiuhao Zeng , Tianze Luo , Boyu Wang

Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one prevailing strategy is…

计算机视觉与模式识别 · 计算机科学 2022-03-01 Xu Ma , Junkun Yuan , Yen-wei Chen , Ruofeng Tong , Lanfen Lin

End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition…

声音 · 计算机科学 2021-06-10 Wenxin Hou , Jindong Wang , Xu Tan , Tao Qin , Takahiro Shinozaki

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…

音频与语音处理 · 电气工程与系统科学 2021-07-26 Disong Wang , Liqun Deng , Yu Ting Yeung , Xiao Chen , Xunying Liu , Helen Meng

Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…

音频与语音处理 · 电气工程与系统科学 2020-09-03 Wei Xia , Jing Huang , John H. L. Hansen

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align with the…

计算机视觉与模式识别 · 计算机科学 2022-04-21 Xinyue Huo , Lingxi Xie , Hengtong Hu , Wengang Zhou , Houqiang Li , Qi Tian

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…

声音 · 计算机科学 2022-09-27 Long Mai , Julie Carson-Berndsen

Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone…

计算机视觉与模式识别 · 计算机科学 2022-11-28 Qianyu Zhou , Zhengyang Feng , Qiqi Gu , Guangliang Cheng , Xuequan Lu , Jianping Shi , Lizhuang Ma

Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies…

计算机视觉与模式识别 · 计算机科学 2024-10-24 Indrajeet Ghosh , Garvit Chugh , Abu Zaher Md Faridee , Nirmalya Roy

Robust Unsupervised Domain Adaptation (RoUDA) aims to achieve not only clean but also robust cross-domain knowledge transfer from a labeled source domain to an unlabeled target domain. A number of works have been conducted by directly…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Jia-Li Yin , Haoyuan Zheng , Ximeng Liu

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…

计算机视觉与模式识别 · 计算机科学 2020-08-26 Chuan-Xian Ren , Pengfei Ge , Peiyi Yang , Shuicheng Yan

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…

计算机视觉与模式识别 · 计算机科学 2019-08-20 Tuan-Hung Vu , Himalaya Jain , Maxime Bucher , Matthieu Cord , Patrick Pérez

Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Ting Li , Jianshu Chao , Deyu An

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

计算机视觉与模式识别 · 计算机科学 2019-05-14 Songsong Wu , Yan Yan , Hao Tang , Jianjun Qian , Jian Zhang , Xiao-Yuan Jing

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground…

计算机视觉与模式识别 · 计算机科学 2021-03-10 Xiaoqing Guo , Chen Yang , Baopu Li , Yixuan Yuan

Unsupervised domain adaptation (UDA) aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization…

机器学习 · 计算机科学 2022-10-18 Haiteng Zhao , Chang Ma , Qinyu Chen , Zhi-Hong Deng

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

机器学习 · 计算机科学 2022-01-07 Kowshik Thopalli , Jayaraman J Thiagarajan , Rushil Anirudh , Pavan K Turaga

In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss, that can adapt to the…

计算与语言 · 计算机科学 2021-04-16 Constantinos Karouzos , Georgios Paraskevopoulos , Alexandros Potamianos

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…

声音 · 计算机科学 2021-09-01 Zhengyang Chen , Shuai Wang , Yanmin Qian
‹ 上一页 1 2 3 10 下一页 ›