相关论文: Analysis and Extension of Noisy-target Training fo…

Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of…

Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they must be recorded in a studio. This requirement currently…

The lack of clean speech is a practical challenge to the development of speech enhancement systems, which means that there is an inevitable mismatch between their training criterion and evaluation metric. In response to this unfavorable…

Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the…

In traditional speech denoising tasks, clean audio signals are often used as the training target, but absolutely clean signals are collected from expensive recording equipment or in studios with the strict environments. To overcome this…

Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider learning in isolation, using one-hot encoded labels as the sole…

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…

Supervised learning is a mainstream approach to audio signal enhancement (SE) and requires parallel training data consisting of both noisy signals and the corresponding clean signals. Such data can only be synthesised and are mismatched…

Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training text sentences while with only…

The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research area of training…

Noise in seismic data arises from numerous sources and is continually evolving. The use of supervised deep learning procedures for denoising of seismic datasets often results in poor performance: this is due to the lack of noise-free field…

Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework…

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms. Previous efforts tend to mitigate this problem via…

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…

We propose a novel self-supervised image blind denoising approach in which two neural networks jointly predict the clean signal and infer the noise distribution. Assuming that the noisy observations are independent conditionally to the…

This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization.…

Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in large quantity with a variety of acoustic conditions, many…

Supervised deep networks have achieved promisingperformance on image denoising, by learning image priors andnoise statistics on plenty pairs of noisy and clean images. Unsupervised denoising networks are trained with only noisy images.…

Trace-wise noise is a type of noise often seen in seismic data, which is characterized by vertical coherency and horizontal incoherency. Using self-supervised deep learning to attenuate this type of noise, the conventional blind-trace deep…