PrivacyMic: Utilizing Inaudible Frequencies for Privacy Preserving Daily Activity Recognition

要旨

Sound presents an invaluable signal source that enables computing systems to perform daily activity recognition. However, microphones are optimized for human speech and hearing ranges: capturing private content, such as speech, while omitting useful, inaudible information that can aid in acoustic recognition tasks. We simulated acoustic recognition tasks using sounds from 127 everyday household/workplace objects, finding that inaudible frequencies can act as a substitute for privacy-sensitive frequencies. To take advantage of these inaudible frequencies, we designed a Raspberry Pi-based device that captures inaudible acoustic frequencies with settings that can remove speech or all audible frequencies entirely. We conducted a perception study, where participants "eavesdropped" on PrivacyMic’s filtered audio and found that none of our participants could transcribe speech. Finally, PrivacyMic’s real-world activity recognition performance is comparable to our simulated results, with over 95% classification accuracy across all environments, suggesting immediate viability in performing privacy-preserving daily activity recognition.

受賞
Honorable Mention
著者
Yasha Iravantchi
University of Michigan, Ann Arbor, Michigan, United States
Karan Ahuja
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Mayank Goel
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Chris Harrison
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Alanson Sample
The University of Michigan, Ann Arbor, Michigan, United States
DOI

10.1145/3411764.3445169

論文URL

https://doi.org/10.1145/3411764.3445169

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Interaction Techniques / Sketch and Illustration / Privacy

[B] Paper Room 08, 2021-05-14 01:00:00~2021-05-14 03:00:00 / [C] Paper Room 08, 2021-05-14 09:00:00~2021-05-14 11:00:00 / [A] Paper Room 08, 2021-05-13 17:00:00~2021-05-13 19:00:00
Paper Room 08
13 件の発表
2021-05-14 01:00:00
2021-05-14 03:00:00
日本語まとめ
読み込み中…