Voice localization using nearby wall reflections
Voice localization using nearby wall reflections
复制标题
DOI：
10.1145/3372224.3380884
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Sheng Shen
中科院分区：
文献类型：
--
作者：
Sheng Shen
Amazon Echo（Alexa）和Google Home等语音助手使用麦克风阵列来估计人类语音的到达角度（AoA）。本文的重点是将用户定位作为一种新的功能添加到语音助手中。对于任何语音命令，我们都希望Alexa能够在家中定位用户。核心挑战是双重的：（1）在不知道源信号的情况下准确估计多径回波的AoA，以及（2）追溯这些AoA以反向三角测量用户的位置。我们开发VoLoc，提出了一种改进的多径AoA估计，然后通过误差最小化技术来估计附近的墙壁反射的几何形状的迭代消除和取消算法的系统。然后融合附近墙壁的AoA和几何参数以揭示用户的位置。在适度的假设下，我们报告的定位精度为0.44米，在不同的房间，杂乱，和用户/麦克风的位置。VoLoc几乎是实时运行的，但在开始运行之前需要听到大约15个语音命令。
Voice assistants such as Amazon Echo (Alexa) and Google Home use microphone arrays to estimate the angle of arrival (AoA) of the human voice. This paper focuses on adding user localization as a new capability to voice assistants. For any voice command, we desire Alexa to be able to localize the user inside the home. The core challenge is two-fold: (1) accurately estimating the AoAs of multipath echoes without the knowledge of the source signal, and (2) tracing back these AoAs to reverse triangulate the user's location. We develop VoLoc, a system that proposes an iterative align-and-cancel algorithm for improved multipath AoA estimation, followed by an error-minimization technique to estimate the geometry of a nearby wall reflection. The AoAs and geometric parameters of the nearby wall are then fused to reveal the user's location. Under modest assumptions, we report localization accuracy of 0.44 m across different rooms, clutter, and user/microphone locations. VoLoc runs in near real-time but needs to hear around 15 voice commands before becoming operational.