English

Inferring Facing Direction from Voice Signals

Sound 2021-09-30 v2 Audio and Speech Processing

Abstract

Consider a home or office where multiple devices are running voice assistants (e.g., TVs, lights, ovens, refrigerators, etc.). A human user turns to a particular device and gives a voice command, such as ``Alexa, can you ...''. This paper focuses on the problem of detecting which device the user was facing, and therefore, enabling only that device to respond to the command. Our core intuition emerges from the fact that human voice exhibits a directional radiation pattern, and the orientation of this pattern should influence the signal received at each device. Unfortunately, indoor multipath, unknown user location, and unknown voice signals pose as critical hurdles. Through a new algorithm that estimates the line-of-sight (LoS) power from a given signal, and combined with beamforming and triangulation, we design a functional solution called CoDIR. Results from 500+500+ configurations, across 55 rooms and 99 different users, are encouraging. While improvements are necessary, we believe this is an important step forward in a challenging but urgent problem space.

Keywords

Cite

@article{arxiv.2109.13094,
  title  = {Inferring Facing Direction from Voice Signals},
  author = {Yu-Lin Wei and Rui Li and Abhinav Mehrotra and Romit Roy Choudhury and Nic Lane},
  journal= {arXiv preprint arXiv:2109.13094},
  year   = {2021}
}

Comments

12 pages, 16 figures

R2 v1 2026-06-24T06:23:05.601Z