A Light Weight Model for Active Speaker Detection

Abstract

Active speaker detection is a challenging task in audiovisual scenario understanding, which aims to detect who is speaking in one or more speakers scenarios. This task has received extensive attention as it is crucial in applications such as speaker diarization, speaker tracking, and automatic video editing. The existing studies try to improve performance by inputting multiple candidate information and designing complex models. Although these methods achieved outstanding performance, their high consumption of memory and computational power make them difficult to be applied in resource-limited scenarios. Therefore, we construct a lightweight active speaker detection architecture by reducing input candidates, splitting 2D and 3D convolutions for audio-visual feature extraction, and applying gated recurrent unit (GRU) with low computational complexity for cross-modal modeling. Experimental results on the AVA-ActiveSpeaker dataset show that our framework achieves competitive mAP performance (94.1% vs. 94.2%), while the resource costs are significantly lower than the state-of-the-art method, especially in model parameters (1.0M vs. 22.5M, about 23×) and FLOPs (0.6G vs. 2.6G, about 4×). In addition, our framework also performs well on the Columbia dataset showing good robustness. The code and model weights are available at https: //github.com/Junhua-Liao/Light-ASD.