A Light Weight Model for Active Speaker Detection-Reference-Cited by-同舟云学术

A Light Weight Model for Active Speaker Detection

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Liao Junhua¹,Duan Haihan²,Feng Kanghui¹,Zhao Wanbing¹,Yang Yanbing¹,Chen Liangyin¹

Affiliation:

1. Sichuan University,College of Computer Science,Chengdu,China

2. The Chinese University of Hong Kong,Shenzhen,China

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10203210.pdf?arnumber=10203210

Reference48 articles.

1. Deep Residual Learning for Image Recognition

2. Facesync: A linear op-erator for measuring synchronization of video facial images and audio tracks;slaney;Advances in neural information processing systems,2000

3. Listen to Look: Action Recognition by Previewing Audio

4. Visual speech recognition with loosely synchronized feature streams

5. Improved Active Speaker Detection based on Optical Flow

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Audio-Visual Child-Adult Speaker Classification in Dyadic Interactions;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Multimodal active speaker detection using cross-attention and contextual information;2024 IEEE International Conference on Consumer Electronics (ICCE);2024-01-06

5. Active Speaker Detection Using Audio, Visual, and Depth Modalities: A Survey;IEEE Access;2024