MAVL: Multiresolution Analysis of Voice Localization

Authors: 

Mei Wang, Wei Sun, and Lili Qiu, The University of Texas at Austin

Abstract: 

The ability for a smart speaker to localize a user based on his/her voice opens the door to many new applications. In this paper, we present a novel system, MAVL, to localize human voice. It consists of three major components: (i) We first develop a novel multi-resolution analysis to estimate the AoA of time-varying low-frequency coherent voice signals coming from multiple propagation paths; (ii) We then automatically estimate the room structure by emitting acoustic signals and developing an improved 3D MUSIC algorithm; (iii) We finally re-trace the paths using the estimated AoA and room structure to localize the voice. We implement a prototype system using a single speaker and a uniform circular microphone array. Our results show that it achieves median errors of 1.49o and 3.33o for the top two AoAs estimation and achieves median localization errors of 0.31m in line-of-sight (LoS) cases and 0.47m in non-line-of-sight (NLoS) cases.

NSDI '21 Open Access Sponsored by NetApp

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {262015,
author = {Mei Wang and Wei Sun and Lili Qiu},
title = {{MAVL}: Multiresolution Analysis of Voice Localization},
booktitle = {18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)},
year = {2021},
isbn = {978-1-939133-21-2},
pages = {845--858},
url = {https://www.usenix.org/conference/nsdi21/presentation/wang},
publisher = {USENIX Association},
month = apr
}

Presentation Video