Current methods for active speak er detection focus on modeling short-term
audiovisual information from a single speaker. Although this strategy can be
enough for addressing single-speaker scenarios, it prevents accurate detection
when the task is to identify who of many candidate speakers are talking. This
paper introduces the Active Speaker Context, a novel representation that models
relationships between multiple speakers over long time horizons. Our Active
Speaker Context is designed to learn pairwise and temporal relations from an
structured ensemble of audio-visual observations. Our experiments show that a
structured feature ensemble already benefits the active speaker detection
performance. Moreover, we find that the proposed Active Speaker Context
improves the state-of-the-art on the AVA-ActiveSpeaker dataset achieving a mAP
of 87.1%. We present ablation studies that verify that this result is a direct
consequence of our long-term multi-speaker analysis.

该论文提出了一种新的表示方法 Active Speaker Context，用于学习音视频观察中多个发言人之间的关系，并通过多态结构获得更好的检测表现，最终在 AVA-ActiveSpeaker 数据集上获得 mAP 为 87.1% 的优秀成果。

情境中的主动说话者

Active Speakers in Context

This report describes our submission to the ActivityNet Challenge at CVPR
2019. We use a 3D convolutional neural network (CNN) based front-end and an
ensemble of temporal convolution and LSTM classifiers to predict whether a
visible person is speaking or not. Our results show significant improvements
over the baseline on the AVA-ActiveSpeaker dataset.

本研究使用 3D 卷积神经网络和一组时间卷积和 LSTM 分类器，对可见人是否在说话进行预测，从而在 AVS-ActiveSpeaker 数据集上获得了显著的改进。