English
Related papers

Related papers: Improved Techniques for the Conditional Generative…

200 papers

The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-20 Chenda Li , Wangyou Zhang , Wei Wang , Robin Scheibler , Kohei Saijo , Samuele Cornell , Yihui Fu , Marvin Sach , Zhaoheng Ni , Anurag Kumar , Tim Fingscheidt , Shinji Watanabe , Yanmin Qian

We present a novel data augmentation method to address the challenge of data scarcity in modeling longitudinal patterns in Electronic Health Records (EHR) of patients using natural language processing (NLP) algorithms. The proposed method…

Machine Learning · Computer Science 2024-02-29 Sunwoong Choi , Samuel Kim

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…

Computation and Language · Computer Science 2018-12-18 Xing Wu , Shangwen Lv , Liangjun Zang , Jizhong Han , Songlin Hu

Medical datasets often face the problem of data scarcity, as ground truth labels must be generated by medical professionals. One mitigation strategy is to pretrain deep learning models on large, unlabelled datasets with self-supervised…

Machine Learning · Computer Science 2022-11-16 Jessica Y. Bo , Hen-Wei Huang , Alvin Chan , Giovanni Traverso

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

Sound · Computer Science 2020-11-02 Jaesung Huh , Hee Soo Heo , Jingu Kang , Shinji Watanabe , Joon Son Chung

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts…

Sound · Computer Science 2024-09-04 Chien-Chun Wang , Li-Wei Chen , Hung-Shin Lee , Berlin Chen , Hsin-Min Wang

Data augmentation, a widely-employed technique for addressing data scarcity, involves generating synthetic data examples which are then used to augment available training data. Researchers have seen surprising success from simple methods,…

Computation and Language · Computer Science 2025-06-05 Ray Groshan , Michael Ginn , Alexis Palmer

Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-04 Kaiqi Fu , Shaojun Gao , Kai Wang , Wei Li , Xiaohai Tian , Zejun Ma

In this paper, we propose a novel data augmentation technique called GenMix, which combines generative and mixture approaches to leverage the strengths of both methods. While generative models excel at creating new data patterns, they face…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Hansang Lee , Haeil Lee , Helen Hong

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Asad Ullah , Alessandro Ragano , Andrew Hines

Vocoder models have recently achieved substantial progress in generating authentic audio comparable to human quality while significantly reducing memory requirement and inference time. However, these data-hungry generative models require…

Sound · Computer Science 2023-12-19 Haoming Guo , Seth Z. Zhao , Jiachen Lian , Gopala Anumanchipalli , Gerald Friedland

Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works in neural text generative models, particularly latent…

Computation and Language · Computer Science 2018-11-07 Kang Min Yoo , Youhyun Shin , Sang-goo Lee

Current medical image synthetic augmentation techniques rely on intensive use of generative adversarial networks (GANs). However, the nature of GAN architecture leads to heavy computational resources to produce synthetic images and the…

Image and Video Processing · Electrical Eng. & Systems 2022-12-21 Meng Li , Brian Lovell

Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequences. A critical yet underexplored factor in training these models is data augmentation, the…

Machine Learning · Computer Science 2026-05-21 Geon Lee , Bhuvesh Kumar , Clark Mingxuan Ju , Tong Zhao , Kijung Shin , Neil Shah , Liam Collins

Over the years, the paradigm of medical image analysis has shifted from manual expertise to automated systems, often using deep learning (DL) systems. The performance of deep learning algorithms is highly dependent on data quality.…

Image and Video Processing · Electrical Eng. & Systems 2022-10-04 Sidra Aleem , Teerath Kumar , Suzanne Little , Malika Bendechache , Rob Brennan , Kevin McGuinness

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…

Computation and Language · Computer Science 2021-09-06 Yingmei Guo , Linjun Shou , Jian Pei , Ming Gong , Mingxing Xu , Zhiyong Wu , Daxin Jiang

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the…

Sound · Computer Science 2021-02-22 Houjun Huang , Xu Xiang , Fei Zhao , Shuai Wang , Yanmin Qian

Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on automatic data augmentation learn a policy to form a sequence of…

Machine Learning · Computer Science 2022-11-03 Kaiwen Yang , Yanchao Sun , Jiahao Su , Fengxiang He , Xinmei Tian , Furong Huang , Tianyi Zhou , Dacheng Tao

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-17 Haoyu Li , Junichi Yamagishi

Electroencephalogram (EEG) classification has been widely used in various medical and engineering applications, where it is important for understanding brain function, diagnosing diseases, and assessing mental health conditions. However,…

Signal Processing · Electrical Eng. & Systems 2024-08-20 Mingzhi Chen , Yiyu Gui , Yuqi Su , Yuesheng Zhu , Guibo Luo , Yuchao Yang
‹ Prev 1 4 5 6 7 8 10 Next ›