English
Related papers

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

200 papers

Automatic Speech Recognition (ASR) systems, despite large multilingual training, struggle in low-resource scenarios where labeled data is scarce. We propose BEARD (BEST-RQ Encoder Adaptation with Re-training and Distillation), a novel…

Computation and Language · Computer Science 2026-05-13 Raphaël Bagat , Irina Illina , Emmanuel Vincent

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Sound · Computer Science 2022-10-07 Yehoshua Dissen , Felix Kreuk , Joseph Keshet

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor…

Computation and Language · Computer Science 2025-05-22 Weiting Tan , Yunmo Chen , Tongfei Chen , Guanghui Qin , Haoran Xu , Heidi C. Zhang , Benjamin Van Durme , Philipp Koehn

For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Chi-Chang Lee , Cheng-Hung Hu , Yu-Chen Lin , Chu-Song Chen , Hsin-Min Wang , Yu Tsao

Recent breakthroughs in singing voice synthesis (SVS) have heightened the demand for high-quality annotated datasets, yet manual annotation remains prohibitively labor-intensive and resource-intensive. Existing automatic singing annotation…

Sound · Computer Science 2025-07-10 Wenxiang Guo , Yu Zhang , Changhao Pan , Zhiyuan Zhu , Ruiqi Li , Zhetao Chen , Wenhao Xu , Fei Wu , Zhou Zhao

This work presents STAR, the first end-to-end speech-to-audio generation framework, designed to enhance efficiency and address error propagation inherent in cascaded systems. Unlike prior approaches relying on text or vision, STAR leverages…

Sound · Computer Science 2025-09-23 Zeyu Xie , Xuenan Xu , Yixuan Li , Mengyue Wu , Yuexian Zou

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

Machine Learning · Computer Science 2019-11-20 Qian Wang , Toby P. Breckon

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…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Indrajeet Ghosh , Garvit Chugh , Abu Zaher Md Faridee , Nirmalya Roy

Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models trained through SSL are biased to the pretraining data…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-17 Ruchao Fan , Abeer Alwan

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…

Computation and Language · Computer Science 2022-05-04 Alexei Baevski , Wei-Ning Hsu , Alexis Conneau , Michael Auli

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Caiyuan Zheng , Hui Li , Seon-Min Rhee , Seungju Han , Jae-Joon Han , Peng Wang

Speech recognition systems often struggle with data domains that have not been included in the training. To address this, unsupervised domain adaptation has been explored with ensemble and multi-stage teacher-student training methods…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-14 Rehan Ahmad , Muhammad Umar Farooq , Qihang Feng , Thomas Hain

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-12 Changhan Wang , Juan Pino , Jiatao Gu

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Computation and Language · Computer Science 2024-10-07 Christopher Schröder , Gerhard Heyer

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Computation and Language · Computer Science 2026-02-24 Zefang Liu , Chenyang Zhu , Sangwoo Cho , Shi-Xiong Zhang

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…

Computation and Language · Computer Science 2023-05-23 Zhengxiang Shi , Francesco Tonolini , Nikolaos Aletras , Emine Yilmaz , Gabriella Kazai , Yunlong Jiao

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 L. Xiao , J. Xu , D. Zhao , Z. Wang , L. Wang , Y. Nie , B. Dai

Unsupervised domain adaptation (UDA) assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. However, considering the data privacy and the inefficiency of data transmission, it…

Computer Vision and Pattern Recognition · Computer Science 2020-12-11 Xianfeng Li , Weijie Chen , Di Xie , Shicai Yang , Peng Yuan , Shiliang Pu , Yueting Zhuang

Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Jogendra Nath Kundu , Akshay Kulkarni , Amit Singh , Varun Jampani , R. Venkatesh Babu