English
Related papers

Related papers: Feature Aggregation in Joint Sound Classification …

200 papers

Sound Event Localization and Detection (SELD) is a problem related to the field of machine listening whose objective is to recognize individual sound events, detect their temporal activity, and estimate their spatial location. Thanks to the…

Recent years have witnessed promising results of face detection using deep learning. Despite making remarkable progresses, face detection in the wild remains an open research challenge especially when detecting faces at vastly different…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Jialiang Zhang , Xiongwei Wu , Jianke Zhu , Steven C. H. Hoi

Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…

Sound · Computer Science 2023-02-01 Tung-Yu Wu , Chen-An Li , Tzu-Han Lin , Tsu-Yuan Hsu , Hung-Yi Lee

While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Yunqi Miao , Zijia Lin , Guiguang Ding , Jungong Han

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin

Electroencephalogram (EEG)-based P300 speller brain-computer interfaces (BCIs) face three main challenges: low signal-to-noise ratio (SNR), poor generalization, and time-consuming calibration. We propose SpellerSSL, a framework that…

Signal Processing · Electrical Eng. & Systems 2025-11-25 Jiazhen Hong , Geoff Mackellar , Soheila Ghane

Semantic segmentation is an essential part of deep learning. In recent years, with the development of remote sensing big data, semantic segmentation has been increasingly used in remote sensing. Deep convolutional neural networks (DCNNs)…

Computer Vision and Pattern Recognition · Computer Science 2021-05-31 Xuan Yang , Shanshan Li , Zhengchao Chen , Jocelyn Chanussot , Xiuping Jia , Bing Zhang , Baipeng Li , Pan Chen

The task of instance segmentation in remote sensing images, aiming at performing per-pixel labeling of objects at instance level, is of great importance for various civil applications. Despite previous successes, most existing instance…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Ye Liu , Huifang Li , Chao Hu , Shuang Luo , Yan Luo , Chang Wen Chen

Environmental Sound Classification (ESC) is an important and challenging problem, and feature representation is a critical and even decisive factor in ESC. Feature representation ability directly affects the accuracy of sound…

Sound · Computer Science 2019-08-19 Tianhao Qiao , Shunqing Zhang , Zhichao Zhang , Shan Cao , Shugong Xu

Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information…

Sound · Computer Science 2020-05-22 Helin Wang , Yuexian Zou , Dading Chong , Wenwu Wang

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level…

Computer Vision and Pattern Recognition · Computer Science 2016-04-20 Gayoung Lee , Yu-Wing Tai , Junmo Kim

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Phani Sankar Nidadavolu , Saurabh Kataria , Paola García-Perera , Jesús Villalba , Najim Dehak

Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering properties, magically in the absence of label supervision.…

Machine Learning · Computer Science 2025-05-13 Xi Weng , Jianing An , Xudong Ma , Binhang Qi , Jie Luo , Xi Yang , Jin Song Dong , Lei Huang

The integration of Federated Learning (FL) and Self-supervised Learning (SSL) offers a unique and synergetic combination to exploit the audio data for general-purpose audio understanding, without compromising user data privacy. However,…

Sound · Computer Science 2024-02-07 Yasar Abbas Ur Rehman , Kin Wai Lau , Yuyang Xie , Lan Ma , Jiajun Shen

The weakly supervised sound event detection problem is the task of predicting the presence of sound events and their corresponding starting and ending points in a weakly labeled dataset. A weak dataset associates each training sample (a…

Sound · Computer Science 2021-06-22 Mohammad Rasool Izadi , Robert Stevenson , Laura N. Kloepper

Acoustic Scene Classification (ASC) and Sound Event Detection (SED) are two separate tasks in the field of computational sound scene analysis. In this work, we present a new dataset with both sound scene and sound event labels and use this…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-02 Helen L. Bear , Ines Nolasco , Emmanouil Benetos

Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this paper, we explore the use of multi-scale Dense connected…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 Dawei Feng , Kele Xu , Haibo Mi , Feifan Liao , Yan Zhou

The large size of nowadays' online multimedia databases makes retrieving their content a difficult and time-consuming task. Users of online sound collections typically submit search queries that express a broad intent, often making the…

Information Retrieval · Computer Science 2020-06-16 Xavier Favory , Frederic Font , Xavier Serra

Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between…

Machine Learning · Computer Science 2019-05-15 Penghui Sun , Jingwei Qu , Xiaoqing Lyu , Haibin Ling , Zhi Tang

Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral…

Sound · Computer Science 2025-09-16 Friedrich Wolf-Monheim