부산대학교 도서관

Active speaker detection is a challenging task in audiovisual scenarios, with the aim to detect who is speaking in one or more speaker scenarios. This task has received considerable attention because it is crucial in many applications. Existing studies have attempted to improve the performance by inputting multiple candidate information and designing complex models. Although these methods have achieved excellent performance, their high memory and computational power consumption render their application to resource-limited scenarios difficult. Therefore, in this study, a lightweight active speaker detection architecture is constructed by reducing the number of input candidates, splitting 2D and 3D convolutions for audio-visual feature extraction, and applying gated recurrent units with low computational complexity for cross-modal modeling. Experimental results on the AVA-ActiveSpeaker dataset reveal that the proposed framework achieves competitive mAP performance (94.1% vs. 94.2%), while the resource costs are significantly lower than the state-of-the-art method, particularly in model parameters (1.0M vs. 22.5M, approximately 23×) and FLOPs (0.6G vs. 2.6G, approximately 4×). Additionally, the proposed framework also performs well on the Columbia dataset, thus demonstrating good robustness. The code and model weights are available at https://github.com/Junhua-Liao/Light-ASD.