English
Related papers

Related papers: Lungmix: A Mixup-Based Strategy for Generalization…

200 papers

Deep image classifiers often perform poorly when training data are heavily class-imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Hsin-Ping Chou , Shih-Chieh Chang , Jia-Yu Pan , Wei Wei , Da-Cheng Juan

Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a…

Machine Learning · Computer Science 2024-01-23 Yousef El-Laham , Elizabeth Fons , Dillon Daudert , Svitlana Vyetrenko

Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD. In this work, we report a…

Machine Learning · Computer Science 2023-03-03 Zixuan Liu , Ziqiao Wang , Hongyu Guo , Yongyi Mao

We propose a novel method to improve deep learning model performance on highly-imbalanced tasks. The proposed method is based on CycleGAN to achieve balanced dataset. We show that data augmentation with GAN helps to improve accuracy of…

Image and Video Processing · Electrical Eng. & Systems 2019-08-02 Tatiana Malygina , Elena Ericheva , Ivan Drokin

In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…

Machine Learning · Computer Science 2025-12-24 Minsu Kim , Seong-Hyeon Hwang , Steven Euijong Whang

In this paper, we evaluate various deep learning frameworks for detecting respiratory anomalies from input audio recordings. To this end, we firstly transform audio respiratory cycles collected from patients into spectrograms where both…

Sound · Computer Science 2022-01-11 Lam Pham , Dat Ngo , Truong Hoang , Alexander Schindler , Ian McLoughlin

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

Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward…

Sound · Computer Science 2023-11-14 June-Woo Kim , Chihyeon Yoon , Miika Toikkanen , Sangmin Bae , Ho-Young Jung

Respiratory sound datasets are limited in size and quality, making high performance difficult to achieve. Ensemble models help but inevitably increase compute cost at inference time. Soft label training distills knowledge efficiently with…

Sound · Computer Science 2025-05-29 Miika Toikkanen , June-Woo Kim

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…

Computation and Language · Computer Science 2021-02-26 Linghui Meng , Jin Xu , Xu Tan , Jindong Wang , Tao Qin , Bo Xu

Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-13 Yun-Ning Hung , Alexander Lerch

Analysis of respiratory sounds increases its importance every day. Many different methods are available in the analysis, and new techniques are continuing to be developed to further improve these methods. Features are extracted from audio…

Sound · Computer Science 2021-01-22 Osman Balli , Yakup Kutlu

Machine learning techniques are used in a wide range of domains. However, machine learning models often suffer from the problem of over-fitting. Many data augmentation methods have been proposed to tackle such a problem, and one of them is…

Machine Learning · Statistics 2021-06-21 Masanari Kimura

A new method for the classification of respiratory diseases is presented. The method is based on a novel class of features, extracted from pulmonary sounds, by parameterizing their spectrograms that are represented as surfaces, and by…

Signal Processing · Electrical Eng. & Systems 2021-06-07 Jeremy Levy , Alexander Naitsat , Yehoshua Y. Zeevi

Large language models have demonstrated remarkable capabilities across various tasks, primarily attributed to the utilization of diversely sourced data. However, the impact of pretraining data composition on model performance remains poorly…

Machine Learning · Computer Science 2025-01-28 Ce Ge , Zhijian Ma , Daoyuan Chen , Yaliang Li , Bolin Ding

In medical image analysis, regression plays a critical role in computer-aided diagnosis. It enables quantitative measurements such as age prediction from structural imaging, cardiac function quantification, and molecular measurement from…

Machine Learning · Computer Science 2025-03-25 Yilei Wu , Zijian Dong , Chongyao Chen , Wangchunshu Zhou , Juan Helen Zhou

Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless training diagram, to improve the generalization of deep…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-01 Oscar Chang , Dung N. Tran , Kazuhito Koishida

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…

Computation and Language · Computer Science 2020-11-12 Lichao Sun , Congying Xia , Wenpeng Yin , Tingting Liang , Philip S. Yu , Lifang He

We introduce PodcastMix, a dataset formalizing the task of separating background music and foreground speech in podcasts. We aim at defining a benchmark suitable for training and evaluating (deep learning) source separation models. To that…

Sound · Computer Science 2022-07-18 Nicolás Schmidt , Jordi Pons , Marius Miron

As the burden of respiratory diseases continues to fall on society worldwide, this paper proposes a high-quality and reliable dataset of human sounds for studying respiratory illnesses, including pneumonia and COVID-19. It consists of…

Sound · Computer Science 2023-08-07 Truong V. Hoang , Quang H. Nguyen , Cuong Q. Nguyen , Phong X. Nguyen , Hoang D. Nguyen