arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1711.11565cs.SDcs.AIcs.MMcs.ROeess.AS
收藏

基于深度神经网络的多说话人检测与定位

Deep Neural Networks for Multiple Speaker Detection and Localization

Idiap Research Institute(Idiap研究所);École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Weipeng He, Petr Motlicek, Jean-Marc Odobez

摘要:

我们建议使用神经网络的同时检测和定位的多个声源在人机交互。与传统的信号处理技术相比,基于神经网络的声源定位方法需要较少的关于环境的强假设。以前的基于神经网络的方法一直专注于定位单个声源,在检测和定位方面没有扩展到多个声源。因此,在本文中,我们提出了一种基于似然的网络输出编码,它自然允许检测任意数量的源。此外,我们研究了使用子带互相关信息作为更好地定位在声音混合的功能,以及三种不同的网络架构,基于不同的动机。从机器人记录的真实数据的实验表明,我们提出的方法显着优于流行的基于空间谱的方法。

英文摘要:

We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction. In contrast to conventional signal processing techniques, neural network-based sound source localization methods require fewer strong assumptions about the environment. Previous neural network-based methods have been focusing on localizing a single sound source, which do not extend to multiple sources in terms of detection and localization. In this paper, we thus propose a likelihood-based encoding of the network output, which naturally allows the detection of an arbitrary number of sources. In addition, we investigate the use of sub-band cross-correlation information as features for better localization in sound mixtures, as well as three different network architectures based on different motivations. Experiments on real data recorded from a robot show that our proposed methods significantly outperform the popular spatial spectrum-based approaches.

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。

↑