English
Related papers

Related papers: Data Augmentation for Environmental Sound Classifi…

200 papers

This report presents the comprehensive implementation, evaluation, and optimization of Denoising Diffusion Probabilistic Models (DDPMs) and Denoising Diffusion Implicit Models (DDIMs), which are state-of-the-art generative models. During…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Jaineet Shah , Michael Gromis , Rickston Pinto

Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result in poor generalization, where models overfit to dominant…

Computation and Language · Computer Science 2025-01-14 Ashok Choudhary , Cornelius Thiels , Hojjat Salehinejad

Deep learning based medical image recognition systems often require a substantial amount of training data with expert annotations, which can be expensive and time-consuming to obtain. Recently, synthetic augmentation techniques have been…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Jiarong Ye , Haomiao Ni , Peng Jin , Sharon X. Huang , Yuan Xue

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-26 Heming Wang , Eric W. Healy , DeLiang Wang

Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Taesun Yeom , Minhyeok Lee

Environmental sound classification (ESC) is an important and challenging problem. In contrast to speech, sound events have noise-like nature and may be produced by a wide variety of sources. In this paper, we propose to use a novel deep…

Sound · Computer Science 2018-08-28 Zhichao Zhang , Shugong Xu , Shan Cao , Shunqing Zhang

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-22 Bunlong Lay , Rostislav Makarov , Simon Welker , Maris Hillemann , Timo Gerkmann

Data augmentation is a widely used technique in many machine learning tasks, such as image classification, to virtually enlarge the training dataset size and avoid overfitting. Traditional data augmentation techniques for image…

Machine Learning · Computer Science 2018-04-12 Hiroshi Inoue

In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Sanberk Serbest , Tijana Stojkovic , Milos Cernak , Andrew Harper

The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets, facilitating the accurate classification of modulation…

Machine Learning · Computer Science 2023-11-08 Tao Chen , Shilian Zheng , Kunfeng Qiu , Luxin Zhang , Qi Xuan , Xiaoniu Yang

Data augmentation is one of the most common tools in deep learning, underpinning many recent advances including tasks such as classification, detection, and semantic segmentation. The standard approach to data augmentation involves simple…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Fulong Ma , Weiqing Qi , Guoyang Zhao , Ming Liu , Jun Ma

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Sound · Computer Science 2026-05-01 Alexandre R. Ferreira , Cláudio E. C. Campelo

Training deep learning methods on small time series datasets that also include corrupted samples is challenging. Diffusion models have shown to be effective to generate realistic and synthetic data, and correct corrupted samples through…

Machine Learning · Computer Science 2025-09-17 Julian Ripper , Ousama Esbel , Rafael Fietzek , Max Mühlhäuser , Thomas Kreutz

Recent advancements in deep generative modeling make it possible to learn prior distributions from complex data that subsequently can be used for Bayesian inference. However, we find that distributions learned by deep generative models for…

Machine Learning · Computer Science 2020-11-04 Maurice Frank , Maximilian Ilse

It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning-based predictive methods, diffusion-based generative models…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Jie Zhang , Haoyin Yan , Xiaofei Li

While recommender systems have become an integral component of the Web experience, their heavy reliance on user data raises privacy and security concerns. Substituting user data with synthetic data can address these concerns, but accurately…

Information Retrieval · Computer Science 2024-06-21 Derek Lilienthal , Paul Mello , Magdalini Eirinaki , Stas Tiomkin

Diffusion models have emerged as an expressive family of generative models rivaling GANs in sample quality and autoregressive models in likelihood scores. Standard diffusion models typically require hundreds of forward passes through the…

Machine Learning · Computer Science 2022-02-14 Daniel Watson , William Chan , Jonathan Ho , Mohammad Norouzi

Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Quang-Huy Che , Duc-Tri Le , Bich-Nga Pham , Duc-Khai Lam , Vinh-Tiep Nguyen

Deep learning models in the Earth Observation domain heavily rely on the availability of large-scale accurately labeled satellite imagery. However, obtaining and labeling satellite imagery is a resource-intensive endeavor. While generative…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Orkhan Baghirli , Hamid Askarov , Imran Ibrahimli , Ismat Bakhishov , Nabi Nabiyev

Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-29 Shrishti Saha Shetu , Emanuël A. P. Habets , Andreas Brendel