相关论文: Disentangling Hierarchical Features for Anomalous …

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen…

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…

This work introduces a novel deep learning-based approach for gravitational wave anomaly detection, aiming to overcome the limitations of traditional matched filtering techniques in identifying unknown waveform gravitational wave signals.…

Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Domain Generalization…

Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approaches leverage…

This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds…

High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR…

In this work, we present a novel approach to transform supervised classifiers into effective unsupervised anomaly detectors. The method we have developed, termed Discriminatory Detection of Distortions (DDD), enhances anomaly detection by…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to align features across domains by fooling a special domain…

The problem of Domain Adaptive in the field of Object Detection involves the transfer of object detection models from labeled source domains to unannotated target domains. Recent advancements in this field aim to address domain…

Articulatory features are inherently invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition (ASR) systems for normal speech. Their practical application to disordered speech…

Noises are common events in seismic reflection data that have very striking features in seismograms, affecting seismic data processing and interpretation. Noise attenuation is an essential phase in seismic processing data, usually resulting…

Different machines can exhibit diverse frequency patterns in their emitted sound. This feature has been recently explored in anomaly sound detection and reached state-of-the-art performance. However, existing methods rely on the manual or…

Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students…

Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification…

Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…