arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.11280cs.LGcs.SDeess.ASstat.ML
收藏

从视觉到听觉问答

From Visual to Acoustic Question Answering

Sherbrooke University(舍布鲁克大学);KTH Royal Institute of Technology(KTH皇家理工学院)

Jerome Abdelnour, Giampiero Salvi, Jean Rouat

摘要:

本文介绍了声学问答(AQA)这一新课题,以促进声学推理的研究。AQA任务包括分析由基本声音组合组成的声学场景,并回答与这些声音的位置和属性相关的问题。所问的这种关系问题要求模型执行非平凡的推理,以便正确回答。虽然类似的问题已被广泛研究的视觉推理领域,我们不知道任何以前的研究解决问题的声学域。我们提出了一种方法,从基本的声音和一些相关的问题,每个场景使用模板生成的声学场景。我们还提出了两个模型(电影和MAC),已被证明是工作的视觉推理所获得的初步结果。

英文摘要:

We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions asked, require that the models perform non-trivial reasoning in order to answer correctly. Although similar problems have been extensively studied in the domain of visual reasoning, we are not aware of any previous studies addressing the problem in the acoustic domain. We propose a method for generating the acoustic scenes from elementary sounds and a number of relevant questions for each scene using templates. We also present preliminary results obtained with two models (FiLM and MAC) that have been shown to work for visual reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑