Takashi Oya*, Shohei Iwase*, Ryota Natsume, Takahiro Itazuri, Shugo Yamaguchi, Shigeo Morishima
Do We Need Sound for Sound Source Localization?
Asian Conference on Computer Vision 2020
During the performance of sound source localization which uses both visual and aural information, it presently remains unclear how much either image or sound modalities contribute to the result, i.e Download the game above. do we need both image and sound for sound source localization? To address this question, we develop an unsupervised learning system that solves sound source localization by decomposing this task into two steps: (i) “potential sound source localization”, a step that localizes possible sound sources using only visual information (ii) “object selection”, a step that identifies which objects are actually sounding using aural information 엑시트 고화질. Our overall system achieves state-of-the-art performance in sound source localization, and more importantly, we find that despite the constraint on available information, the results of (i) achieve similar performance 박윤선 주석 다운로드. From this observation and further experiments, we show that visual information is dominant in “sound” source localization when evaluated with the currently adopted benchmark dataset 아마존 에코. Moreover, we show that the majority of sound-producing objects within the samples in this dataset can be inherently identified using only visual information, and thus that the dataset is inadequate to evaluate a system’s capability to leverage aural information Download Spider Solitaire. As an alternative, we present an evaluation protocol that enforces both visual and aural information to be leveraged, and verify this property through several experiments Download internet YouTube.