English
Related papers

Related papers: Data augmentation and loss normalization for deep …

200 papers

In this study, we conduct a comparative analysis of deep learning-based noise reduction methods in low signal-to-noise ratio (SNR) scenarios. Our investigation primarily focuses on five key aspects: The impact of training data, the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-28 Shrishti Saha Shetu , Emanuël A. P. Habets , Andreas Brendel

Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Alex Hernández-García , Peter König

Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of the network to be similar in the vicinity of the observed…

Machine Learning · Computer Science 2021-10-05 Erik Englesson , Hossein Azizpour

Data augmentation in deep neural networks is the process of generating artificial data in order to reduce the variance of the classifier with the goal to reduce the number of errors. This idea has been shown to improve deep neural network's…

Computer Vision and Pattern Recognition · Computer Science 2018-08-08 Hassan Ismail Fawaz , Germain Forestier , Jonathan Weber , Lhassane Idoumghar , Pierre-Alain Muller

Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-15 Zengrui Jin , Xurong Xie , Tianzi Wang , Mengzhe Geng , Jiajun Deng , Guinan Li , Shujie Hu , Xunying Liu

This paper studies the Speech Enhancement based on Deep Neural Networks. The proposed architecture gradually follows the signal transformation during enhancement by means of a visualization probe at each network block. Alongside the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-10 Jorge Llombart , Dayana Ribas , Antonio Miguel , Luis Vicente , Alfonso Ortega , Eduardo Lleida

This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative models as an additional dataset for classification with small…

Machine Learning · Computer Science 2023-10-24 Shin'ya Yamaguchi , Daiki Chijiwa , Sekitoshi Kanai , Atsutoshi Kumagai , Hisashi Kashima

Recent interest in exploiting Deep Learning techniques for Noise Suppression, has led to the creation of Hybrid Denoising Systems that combine classic Signal Processing with Deep Learning. In this paper, we concentrated our efforts on…

Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target. To relax the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-19 Yu-Che Wang , Shrikant Venkataramani , Paris Smaragdis

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…

Computer Vision and Pattern Recognition · Computer Science 2019-01-23 Cecilia Summers , Michael J. Dinneen

Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-21 Bhavya Ghai , Buvana Ramanan , Klaus Mueller

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…

Sound · Computer Science 2017-12-19 Santiago Pascual , Maruchan Park , Joan Serrà , Antonio Bonafonte , Kang-Hun Ahn

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

Machine Learning · Computer Science 2018-11-20 Farzan Farnia , Jesse M. Zhang , David Tse

For voice communication, it is important to extract the speech from its noisy version without introducing unnaturally artificial noise. By studying the subband mean-squared error (MSE) of the speech for unsupervised speech enhancement…

Sound · Computer Science 2019-12-10 Andong Li , Chengshi Zheng , Xiaodong Li

Data augmentation is a key practice in machine learning for improving generalization performance. However, finding the best data augmentation hyperparameters requires domain knowledge or a computationally demanding search. We address this…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Saypraseuth Mounsaveng , Issam Laradji , Ismail Ben Ayed , David Vazquez , Marco Pedersoli

Diffusion models are typically trained using pointwise reconstruction objectives that are agnostic to the spectral and multi-scale structure of natural signals. We propose a loss-level spectral regularization framework that augments…

Machine Learning · Computer Science 2026-03-04 Satish Chandran , Nicolas Roque dos Santos , Yunshu Wu , Greg Ver Steeg , Evangelos Papalexakis

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Machine Learning · Computer Science 2016-06-03 Yang Song , Alexander G. Schwing , Richard S. Zemel , Raquel Urtasun

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

Computer Vision and Pattern Recognition · Computer Science 2017-12-14 Luis Perez , Jason Wang

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model…

Sound · Computer Science 2024-06-21 Li Li , Shogo Seki

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set…

Machine Learning · Statistics 2017-02-21 Terrance DeVries , Graham W. Taylor