Related papers: IMPACT: Industrial Machine Perception via Acoustic…

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs and questions) to…

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However, it has two critical limitations: the lack of global context…

We introduce EPIC-SOUNDS, a large-scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos. We propose an annotation pipeline where annotators temporally label…

The ability to generalize to a wide range of recording devices is a crucial performance factor for audio classification models. The characteristics of different types of microphones introduce distributional shifts in the digitized audio…

Intelligent transport systems (ITS) are pivotal in the development of sustainable and green urban living. ITS is data-driven and enabled by the profusion of sensors ranging from pneumatic tubes to smart cameras. This work explores a novel…

Factory machinery is prone to failure or breakdown, resulting in significant expenses for companies. Hence, there is a rising interest in machine monitoring using different sensors including microphones. In the scientific community, the…

In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial…

Truly intelligent agents need to capture the interplay of all their senses to build a rich physical understanding of their world. In robotics, we have seen tremendous progress in using visual and tactile perception; however, we have often…

Thanks to the development of deep learning, research on machine anomalous sound detection based on self-supervised learning has made remarkable achievements. However, there are differences in the acoustic characteristics of the test set and…

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as…

Learning to produce contact-rich, dynamic behaviors from raw sensory data has been a longstanding challenge in robotics. Prominent approaches primarily focus on using visual or tactile sensing, where unfortunately one fails to capture…

Anomalous Sound Detection (ASD) aims at identifying anomalous sounds from machines and has gained extensive research interests from both academia and industry. However, the uncertainty of anomaly location and much redundant information such…

Existing methods for measuring training sample influence on models only provide static, overall measurements, overlooking how sample influence changes during training. We propose Dynamic Influence Tracker (DIT), which captures the…

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: ``First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring''. The main goal is…

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…

A large and growing amount of speech content in real-life scenarios is being recorded on consumer-grade devices in uncontrolled environments, resulting in degraded speech quality. Transforming such low-quality device-degraded speech into…

Anomaly detection has many important applications, such as monitoring industrial equipment. Despite recent advances in anomaly detection with deep-learning methods, it is unclear how existing solutions would perform under…

Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to identify both seen and unseen anomalies during testing. Current approaches rely on simple…

Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization,…

This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised…