Smart Speaker privacy control - acoustic tagging for Personal Voice Assistants

Thumbnail Image
Cheng, Peng
Bagci, Ibrahim Ethem
Yan, Jeff
Roedig, Utz
Journal Title
Journal ISSN
Volume Title
Published Version
Research Projects
Organizational Units
Journal Issue
Personal Voice Assistants (PVAs) such as the Siri, Amazon Echo and Google Home are now commonplace. PVAs continuously monitor conversations which may be transported to a cloud back end where they are stored, processed and maybe even passed on to other service providers. A user has little controlover this process. She is unable to control the recording behaviour of surrounding PVAs, unable to signal her privacy requirements to back-end systems and unable to track conversation recordings.In this paper we explore techniques for embedding additional information into acoustic signals processed by PVAs. A user employs a tagging device which emits an acoustic signal whenPVA activity is assumed. Any active PVA will embed this tag into their recorded audio stream. The tag may signal a cooperatingPVA or back-end system that a user has not given a recording consent. The tag may also be used to trace when and wherea recording was taken. We discuss different tagging techniques and application scenarios, and we describe the implementation of a prototype tagging device based on PocketSphinx. Using the popular PVA Google Home Mini we demonstrate that the device can tag conversations and that the tagging signal can be retrieved from conversations stored in the Google back-end system.
Smart Speakers , Personal Voice Assistants , Virtual Assistants , Voice controllable systems , Signal tagging , Wake word detection , Acoustic privacy , IoT security and privacy
Cheng, P., Bagci, I. E., Yan, J. and Roedig, U. (2019) 'Smart Speaker privacy control - acoustic tagging for Personal Voice Assistants', IEEE Workshop on the Internet of Safe Things (SafeThings 2019), San Francisco, California, United States, 23 May 2019.
© 2019, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.