English
Related papers

Related papers: Self-Taught Recognizer: Toward Unsupervised Adapta…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Songsong Wu , Yan Yan , Hao Tang , Jianjun Qian , Jian Zhang , Xiao-Yuan Jing

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain…

Machine Learning · Computer Science 2021-01-12 Serban Stan , Mohammad Rostami

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-31 Yang Chen , Weiran Wang , Chao Wang

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…

Computation and Language · Computer Science 2023-06-08 Shikhar Vashishth , Shikhar Bharadwaj , Sriram Ganapathy , Ankur Bapna , Min Ma , Wei Han , Vera Axelrod , Partha Talukdar

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Lingsheng Kong , Bo Hu , Xiongchang Liu , Jun Lu , Jane You , Xiaofeng Liu

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-16 Songjun Cao , Yueteng Kang , Yanzhe Fu , Xiaoshuo Xu , Sining Sun , Yike Zhang , Long Ma

We introduce DAS (Domain Adaptation with Synthetic data), a novel domain adaptation framework for pre-trained ASR model, designed to efficiently adapt to various language-defined domains without requiring any real data. In particular, DAS…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-23 Minh Tran , Yutong Pang , Debjyoti Paul , Laxmi Pandey , Kevin Jiang , Jinxi Guo , Ke Li , Shun Zhang , Xuedong Zhang , Xin Lei

In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English,…

Computation and Language · Computer Science 2023-08-11 Satwinder Singh , Feng Hou , Ruili Wang

Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Negin Ghamsarian , Javier Gamazo Tejero , Pablo Márquez Neila , Sebastian Wolf , Martin Zinkernagel , Klaus Schoeffmann , Raphael Sznitman

In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Mrigank Rochan , Shubhra Aich , Eduardo R. Corral-Soto , Amir Nabatchian , Bingbing Liu

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…

Sound · Computer Science 2021-06-10 Wenxin Hou , Jindong Wang , Xu Tan , Tao Qin , Takahiro Shinozaki

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Chuang Zhu , Kebin Liu , Wenqi Tang , Ke Mei , Jiaqi Zou , Tiejun Huang

This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training data and their…

Computation and Language · Computer Science 2024-07-08 Cong-Thanh Do , Shuhei Imai , Rama Doddipatla , Thomas Hain

Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Xinyang Huang , Chuang Zhu , Bowen Zhang , Shanghang Zhang

Modern robotic systems, deployed across domains from industrial automation to domestic assistance, face a critical challenge: executing tasks with precision and adaptability in dynamic, unpredictable environments. To address this, we…

Robotics · Computer Science 2025-03-11 Md Sadman Sakib , Yu Sun

Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…

Computation and Language · Computer Science 2019-08-26 Kuan-Yu Chen , Che-Ping Tsai , Da-Rong Liu , Hung-Yi Lee , Lin-shan Lee

This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Computation and Language · Computer Science 2023-09-11 Taesik Gong , Josh Belanich , Krishna Somandepalli , Arsha Nagrani , Brian Eoff , Brendan Jou

We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct…

Machine Learning · Computer Science 2012-07-03 Yuan Shi , Fei Sha

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Ke Mei , Chuang Zhu , Jiaqi Zou , Shanghang Zhang