Related papers: Data-Efficient Low-Complexity Acoustic Scene Class…

Audio-visual semantic segmentation (AVSS) represents an extension of the audio-visual segmentation (AVS) task, necessitating a semantic understanding of audio-visual scenes beyond merely identifying sound-emitting objects at the visual…

In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with…

The successful deployment of deep learning-based acoustic echo and noise reduction (AENR) methods in consumer devices has spurred interest in developing low-complexity solutions, while emphasizing the need for robust performance in…

Sound event detection (SED) and acoustic scene classification (ASC) are important research topics in environmental sound analysis. Many research groups have addressed SED and ASC using neural-network-based methods, such as the convolutional…

The primary aim of Audio-Visual Segmentation (AVS) is to precisely identify and locate auditory elements within visual scenes by accurately predicting segmentation masks at the pixel level. Achieving this involves comprehensively…

Recent studies focus on developing efficient systems for acoustic scene classification (ASC) using convolutional neural networks (CNNs), which typically consist of consecutive kernels. This paper highlights the benefits of using separate…

Semantic Scene Completion (SSC) constitutes a pivotal element in autonomous driving perception systems, tasked with inferring the 3D semantic occupancy of a scene from sensory data. To improve accuracy, prior research has implemented…

A good joint training framework is very helpful to improve the performances of weakly supervised audio tagging (AT) and acoustic event detection (AED) simultaneously. In this study, we propose three methods to improve the best…

Many communication systems involve high bandwidth, while sparse, radio frequency (RF) signals. Working with high frequency signals requires appropriate system-level components such as high-speed analog-to-digital converters (ADC). In…

In this work, we compare the performance of three selected techniques in open set acoustic scenes classification (ASC). We test thresholding of the softmax output of a deep network classifier, which is the most popular technique nowadays…

Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements. While…

Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referring cues. The task is challenging because the relevance of different modalities varies…

Anomalous Sound Detection (ASD) has gained significant interest through the application of various Artificial Intelligence (AI) technologies in industrial settings. Though possessing great potential, ASD systems can hardly be readily…

Labelled data are limited and self-supervised learning is one of the most important approaches for reducing labelling requirements. While it has been extensively explored in the image domain, it has so far not received the same amount of…

Previous works on scene classification are mainly based on audio or visual signals, while humans perceive the environmental scenes through multiple senses. Recent studies on audio-visual scene classification separately fine-tune the…

Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs…

Analog-to-Digital Converters (ADCs) are essential components in modern data acquisition systems. A key design challenge is accommodating high dynamic range (DR) input signals without clipping. Existing solutions, such as oversampling,…

In real-world voice conversion applications, environmental noise in source speech and user demands for expressive output pose critical challenges. Traditional ASR-based methods ensure noise robustness but suppress prosody richness, while…

Sound event detection (SED) often suffers from the data deficiency problem. The recent baseline system in the DCASE2023 challenge task 4 leverages the large pretrained self-supervised learning (SelfSL) models to mitigate such restriction,…

Speech segmentation is an essential part of speech translation (ST) systems in real-world scenarios. Since most ST models are designed to process speech segments, long-form audio must be partitioned into shorter segments before translation.…