Home > Research > Publications & Outputs > Smart Speaker Privacy Control - Acoustic Taggin...

Electronic data

View graph of relations

Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants. / Cheng, Peng; Bagci, Ibrahim Ethem; Yan, Jeff; Roedig, Utz.

SafeThings 2019 : IEEE Workshop on the Internet of Safe Things. IEEE, 2019.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Cheng, P, Bagci, IE, Yan, J & Roedig, U 2019, Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants. in SafeThings 2019 : IEEE Workshop on the Internet of Safe Things. IEEE.

APA

Cheng, P., Bagci, I. E., Yan, J., & Roedig, U. (2019). Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants. In SafeThings 2019 : IEEE Workshop on the Internet of Safe Things IEEE.

Vancouver

Cheng P, Bagci IE, Yan J, Roedig U. Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants. In SafeThings 2019 : IEEE Workshop on the Internet of Safe Things. IEEE. 2019

Author

Bibtex

@inproceedings{d779cce905524c46b8dc95e08eae5ee3,
title = "Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants",
abstract = "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. At present, a user has little control over this process. He is unable to control the recording behaviour of surrounding PVAs, is unable to signal his privacy requirements to back-end systems and is 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 when PVA activity is assumed. Any active PVA will embed this tag in the recorded audio stream. The tag may signal a cooperating PVA or back-end system that a user has not given a recording consent. The tag may also be used to trace when and where a recording was taken. In this paper we discuss different tagging techniques and application scenarios. 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.",
keywords = "Smart Speakers, Personal Voice Assistants, Virtual Assistants, Voice Controllable Systems, Signal Tagging, Wake Word Detection, Acoustic Privacy, IoT Security andPrivacy",
author = "Peng Cheng and Bagci, {Ibrahim Ethem} and Jeff Yan and Utz Roedig",
year = "2019",
month = may
day = "23",
language = "English",
booktitle = "SafeThings 2019",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants

AU - Cheng, Peng

AU - Bagci, Ibrahim Ethem

AU - Yan, Jeff

AU - Roedig, Utz

PY - 2019/5/23

Y1 - 2019/5/23

N2 - 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. At present, a user has little control over this process. He is unable to control the recording behaviour of surrounding PVAs, is unable to signal his privacy requirements to back-end systems and is 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 when PVA activity is assumed. Any active PVA will embed this tag in the recorded audio stream. The tag may signal a cooperating PVA or back-end system that a user has not given a recording consent. The tag may also be used to trace when and where a recording was taken. In this paper we discuss different tagging techniques and application scenarios. 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.

AB - 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. At present, a user has little control over this process. He is unable to control the recording behaviour of surrounding PVAs, is unable to signal his privacy requirements to back-end systems and is 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 when PVA activity is assumed. Any active PVA will embed this tag in the recorded audio stream. The tag may signal a cooperating PVA or back-end system that a user has not given a recording consent. The tag may also be used to trace when and where a recording was taken. In this paper we discuss different tagging techniques and application scenarios. 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.

KW - Smart Speakers

KW - Personal Voice Assistants

KW - Virtual Assistants

KW - Voice Controllable Systems

KW - Signal Tagging

KW - Wake Word Detection

KW - Acoustic Privacy

KW - IoT Security andPrivacy

M3 - Conference contribution/Paper

BT - SafeThings 2019

PB - IEEE

ER -