相关论文: Data augmentation and loss normalization for deep …

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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,…

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…

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…