Graph-based active speaker detection in fisheye meeting scenes with spatial spectra
Authors:
- Zhen LiaoZLZhen Liao
- Weiwei JiangWJWeiwei Jiang
- Mengting WangMWMengting Wang
- Xinghao HuangXHXinghao Huang
- Wei XuWXWei Xu
- 12 September 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Abstract
No abstract availableFunding Information
- Ministry of Science and Technology of the People's Republic of China
- National Key Research and Development Program of China (2021YFC3340803)
This publication has 8 references indexed in Scilit:
- LR-ASD: Lightweight and Robust Network for Active Speaker DetectionInternational Journal of Computer Vision, 2025
- Labelled Non-Zero Diffusion Particle Flow SMC-PHD Filtering for Multi-Speaker TrackingIEEE Transactions on Multimedia, 2023
- Structure Aware Multi-Graph Network for Multi-Modal Emotion Recognition in ConversationsIEEE Transactions on Multimedia, 2023
- Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive PairsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- Audio-video fusion strategies for active speaker detection in meetingsMultimedia Tools and Applications, 2022
- Developing a BERT based triple classification model using knowledge graph embedding for question answering systemApplied Intelligence, 2021
- Audio-Visual Tracking of Concurrent SpeakersIEEE Transactions on Multimedia, 2021
- Boosting-Based Multimodal Speaker Detection for Distributed Meeting VideosIEEE Transactions on Multimedia, 2008