paper-with-me

Papers

WASD: A Wilder Active Speaker Detection Dataset

2023-03-09 · Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio, Hugo Proença

Current Active Speaker Detection (ASD) models achieve great results on AVA-ActiveSpeaker (AVA), using only sound and facial features. Although this approach is applicable in movie setups (AVA), it is not suited for less constrained conditions. To demonstrate this limitation, we propose a Wilder Active Speaker Detection (WASD) dataset, with increased difficulty by targeting the two key components of current ASD: audio and face. Grouped into 5 categories, ranging from optimal conditions to surveillance settings, WASD contains incremental challenges for ASD with tactical impairment of audio and face data. We select state-of-the-art models and assess their performance in two groups of WASD: Easy (cooperative settings) and Hard (audio and/or face are specifically degraded). The results show that: 1) AVA trained models maintain a state-of-the-art performance in WASD Easy group, while underperforming in the Hard one, showing the 2) similarity between AVA and Easy data; and 3) training in WASD does not improve models performance to AVA levels, particularly for audio impairment and surveillance settings. This shows that AVA does not prepare models for wild ASD and current approaches are subpar to deal with such conditions. The proposed dataset also contains body data annotations to provide a new source for ASD, and is available at https://github.com/Tiago-Roxo/WASD.

📄 PDF Abstract BibTeX arXiv:2303.05321

Code (1)

tiago-roxo/wasd 공식 구현

Tasks

Active Speaker Detection

Similar Papers 제목 키워드 기반

BIAS: A Body-based Interpretable Active Speaker Approach

2024-12-06 · Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio, Hugo Proença

State-of-the-art Active Speaker Detection (ASD) approaches heavily rely on audio and facial features to perform, which is not a sustainable approach in wild scenarios. Although these methods achieve good results in the s…

Active Speaker DetectionFeature Importance

FabuLight-ASD: Unveiling Speech Activity via Body Language

2024-11-20 · Hugo Carneiro, Stefan Wermter

Active speaker detection (ASD) in multimodal environments is crucial for various applications, from video conferencing to human-robot interaction. This paper introduces FabuLight-ASD, an advanced ASD model that integrate…

Active Speaker Detection

ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection

2024-12-11 · Tiago Roxo, Joana C. Costa, Pedro Inácio, Hugo Proença

State-of-the-art Active Speaker Detection (ASD) approaches mainly use audio and facial features as input. However, the main hypothesis in this paper is that body dynamics is also highly correlated to "speaking" (and "lis…

Active Speaker DetectionFeature Importance

GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

2025-12-17 · Yu Wang, Juhyung Ha, Frangil M. Ramirez, Yuchen Wang 외 arxiv

Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails t…

Active Speaker Detection

The Wilderness Area Data Set: Adapting the Covertype data set for unsupervised learning

2019-01-30 · Richard Hugh Moulton, Jakub Zgraja

Benchmark data sets are of vital importance in machine learning research, as indicated by the number of repositories that exist to make them publicly available. Although many of these are usable in the stream mining cont…

ClusteringGeneral Classification