Revisiting Speech Content Privacy

Jennifer Williams; Junichi Yamagishi; Paul-Gauthier Noé; Cassia Valentini-Botinhao; Jean-François Bonastre

doi:10.21437/SPSC.2021-9

Revisiting Speech Content Privacy

Jennifer Williams, Junichi Yamagishi, Paul-Gauthier Noé, Cassia Valentini-Botinhao, Jean-François Bonastre

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different applications of content privacy, even though this area has been under explored in speech technology research. This paper presents several scenarios that indicate a need for speech content privacy even as the specific techniques to achieve content privacy may necessarily vary. Our discussion includes several different types of content privacy including recoverable and non-recoverable content. Finally, we introduce evaluation strategies as well as describe some of the difficulties that may be encountered.

Original language	English
Title of host publication	Proceedings of 2021 ISCA Symposium on Security & Privacy in Speech Communication
Publisher	International Speech Communication Association
Pages	42-46
Number of pages	5
DOIs	https://doi.org/10.21437/SPSC.2021-9
Publication status	Published - 10 Nov 2021
Event	1st ISCA Symposium of the Security & Privacy in Speech Communication - Virtual Duration: 10 Nov 2021 → 12 Nov 2021 https://www.spsc-symposium2021.de/

Symposium

Symposium	1st ISCA Symposium of the Security & Privacy in Speech Communication
Abbreviated title	SPSC 2021
Period	10/11/21 → 12/11/21
Internet address	https://www.spsc-symposium2021.de/

Keywords / Materials (for Non-textual outputs)

privacy
speech coding
speech recognition

Access to Document

10.21437/SPSC.2021-9Licence: All Rights Reserved

Revisiting Speech Content_WILLIAMS_DOA21092021_AFVAccepted author manuscript, 772 KBLicence: All Rights Reserved

https://www.isca-speech.org/archive/spsc_2021/williams21_spsc.htmlLicence: All Rights Reserved

Cite this

@inproceedings{88af2da661734cc89af4252e03dc1a6b,

title = "Revisiting Speech Content Privacy",

abstract = "In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different applications of content privacy, even though this area has been under explored in speech technology research. This paper presents several scenarios that indicate a need for speech content privacy even as the specific techniques to achieve content privacy may necessarily vary. Our discussion includes several different types of content privacy including recoverable and non-recoverable content. Finally, we introduce evaluation strategies as well as describe some of the difficulties that may be encountered. ",

keywords = "privacy, speech coding, speech recognition",

author = "Jennifer Williams and Junichi Yamagishi and Paul-Gauthier No{\'e} and Cassia Valentini-Botinhao and Jean-Fran{\c c}ois Bonastre",

year = "2021",

month = nov,

day = "10",

doi = "10.21437/SPSC.2021-9",

language = "English",

pages = "42--46",

booktitle = "Proceedings of 2021 ISCA Symposium on Security \& Privacy in Speech Communication",

publisher = "International Speech Communication Association",

address = "France",

note = "1st ISCA Symposium of the Security \& Privacy in Speech Communication , SPSC 2021 ; Conference date: 10-11-2021 Through 12-11-2021",

url = "https://www.spsc-symposium2021.de/",

}

Williams, J, Yamagishi, J, Noé, P-G, Valentini-Botinhao, C & Bonastre, J-F 2021, Revisiting Speech Content Privacy. in Proceedings of 2021 ISCA Symposium on Security & Privacy in Speech Communication. International Speech Communication Association, pp. 42-46, 1st ISCA Symposium of the Security & Privacy in Speech Communication , 10/11/21. https://doi.org/10.21437/SPSC.2021-9

TY - GEN

T1 - Revisiting Speech Content Privacy

AU - Williams, Jennifer

AU - Yamagishi, Junichi

AU - Noé, Paul-Gauthier

AU - Valentini-Botinhao, Cassia

AU - Bonastre, Jean-François

PY - 2021/11/10

Y1 - 2021/11/10

N2 - In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different applications of content privacy, even though this area has been under explored in speech technology research. This paper presents several scenarios that indicate a need for speech content privacy even as the specific techniques to achieve content privacy may necessarily vary. Our discussion includes several different types of content privacy including recoverable and non-recoverable content. Finally, we introduce evaluation strategies as well as describe some of the difficulties that may be encountered.

AB - In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different applications of content privacy, even though this area has been under explored in speech technology research. This paper presents several scenarios that indicate a need for speech content privacy even as the specific techniques to achieve content privacy may necessarily vary. Our discussion includes several different types of content privacy including recoverable and non-recoverable content. Finally, we introduce evaluation strategies as well as describe some of the difficulties that may be encountered.

KW - privacy

KW - speech coding

KW - speech recognition

U2 - 10.21437/SPSC.2021-9

DO - 10.21437/SPSC.2021-9

M3 - Conference contribution

SP - 42

EP - 46

BT - Proceedings of 2021 ISCA Symposium on Security & Privacy in Speech Communication

PB - International Speech Communication Association

T2 - 1st ISCA Symposium of the Security & Privacy in Speech Communication

Y2 - 10 November 2021 through 12 November 2021

ER -

Revisiting Speech Content Privacy

Abstract

Symposium

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this