Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes

For this reason, the sound localization This technical report details our work towards building an performance strongly depends on the video content enhanced audio-visual sound event localization and detection [10]. This makes models prone to erroneous SELD on frames (SELD) network. We build on top of the audio-only with no audio or uncorrelated audio activity. SELDnet23 model and adapt it to be audio-visual by merging We introduce a visual branch into the audio-only SELDnet23 both audio and video information prior to the gated recurrent baseline from the Classification of Acoustic Scenes and unit (GRU) of the audio-only network.