arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.13976cs.SDcs.CVeess.AS
收藏

基于概率空间模型的自监督神经音视频声源定位

Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling

National Institute of Advanced Industrial Science and Technology(日本产业技术综合研究所);Waseda University(早稻田大学)

Yoshiki Masuyama, Yoshiaki Bando, Kohei Yatabe, Yoko Sasaki, Masaki Onishi, Yasuhiro Oikawa

摘要:

在视觉观察范围内检测声源目标对于自主机器人理解周围环境具有重要意义。由于在我们的生活环境中,发声物体具有大量的种类和不同的外观,在实践中标记所有发声物体是不可能的。这就需要自监督学习,它不需要人工标记。大多数传统的自监督学习使用单声道音频信号和图像,并且由于音频信号中的差的空间信息而不能区分具有相似外观的声源对象。针对这一问题,提出了一种基于360°图像和多声道音频信号的自监督训练方法。通过结合多声道音频信号中的空间信息,我们的方法训练深度神经网络(DNN)来区分多个声源对象。我们用于定位图像中声源对象的系统由音频和视觉DNN组成。视觉DNN被训练以定位输入图像内的声源候选。音频DNN验证每个候选是否实际产生声音。这些DNN基于概率空间音频模型以自监督方式联合训练。模拟数据的实验结果表明,我们的方法训练的DNN定位多个扬声器。我们还证明了视觉DNN检测对象,包括说话的游客和特定的展品从真实的数据记录在科学博物馆。

英文摘要:

Detecting sound source objects within visual observation is important for autonomous robots to comprehend surrounding environments. Since sounding objects have a large variety with different appearances in our living environments, labeling all sounding objects is impossible in practice. This calls for self-supervised learning which does not require manual labeling. Most of conventional self-supervised learning uses monaural audio signals and images and cannot distinguish sound source objects having similar appearances due to poor spatial information in audio signals. To solve this problem, this paper presents a self-supervised training method using 360° images and multichannel audio signals. By incorporating with the spatial information in multichannel audio signals, our method trains deep neural networks (DNNs) to distinguish multiple sound source objects. Our system for localizing sound source objects in the image is composed of audio and visual DNNs. The visual DNN is trained to localize sound source candidates within an input image. The audio DNN verifies whether each candidate actually produces sound or not. These DNNs are jointly trained in a self-supervised manner based on a probabilistic spatial audio model. Experimental results with simulated data showed that the DNNs trained by our method localized multiple speakers. We also demonstrate that the visual DNN detected objects including talking visitors and specific exhibits from real data recorded in a science museum.

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。

↑