cs.SDNov 8, 2026

From Sound to Occupancy: Privacy-Aware Audio Sensing for Buildings

Authors: Myeongwon Chae, Seonghyuk Son

Organizations: School of Architecture, University of Illinois Urbana-Champaign · School of Architecture, University of Kentucky

Abstract

Occupancy-based controls regulate lighting and HVAC according to whether a space is in use. Passive infrared (PIR) sensors, the most common choice, respond to motion and can report an occupied room as vacant when its occupants remain still. Sound offers an alternative cue, since seated occupants type, turn pages and cough, but microphones raise privacy concerns. We therefore study a two-stage design: an on-device encoder maps each second of audio to a short embedding, and a server-side temporal model turns the stream of embeddings into an occupancy state. To our knowledge, no publicly available dataset pairs office audio with occupancy labels, so we evaluate the two stages separately on public data. The encoder is trained on synthetic scenes that mix empty-room recordings, room impulse responses, office sounds and read speech, and tested on unseen rooms, recordings and speakers for whether a second contains a sound made by a person. On 11 real office recordings (DCASE 2013) it reaches an AUC of 0.87, against 0.76 for log-mel statistics. Attacks on the transmitted embeddings recover at most 1% of the spoken words, against 94% from log-mel frames, but still identify the speaker among 40 in 69 to 77% of the utterances. Noise-floor normalization with adversarial training, an 8-dimensional embedding, or sending only class probabilities lowers this to 38 to 55% without hurting detection. On HPDmobile, which pairs home occupancy labels with an amplitude envelope of the audio, a causal temporal model pretrained with a hierarchical contrastive loss matches hand-crafted features (AUC 0.75) and does better when only one labelled day per home is available. These results make the two-stage design a practical basis for privacy-aware acoustic occupancy sensing, with speaker identity as the one leak still to close.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Experimental study on surveillance video-based indoor occupancy measurement with occupant-centric control

    Mar 27, 2026Irfan Qaisar, Kailai Sun, Qingshan Jia +1Video SurveillanceBuilding Energy Management

  2. Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks

    Jun 26, 2026Andrew C. Cullen, Neil G. Marchant, Jiani Xie +4ASR EvaluationAdversarial Attacks

  3. AudioTrace: File-Level Membership Detection for Audio Large Language Models

    Nov 16, 2026Guangzhi Sun, Xiao Zhan, Shuai Wang +2LLM AuditingPrivacy Leakage in Language Models