@inproceedings{li-etal-2022-adversarial,
title = "Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection",
author = "Li, Sheng and
Li, Jiyi and
Liu, Qianying and
Gong, Zhuo",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.792",
pages = "7291--7297",
abstract = "With the advent of the General Data Protection Regulation (GDPR) and increasing privacy concerns, the sharing of speech data is faced with significant challenges. Protecting the sensitive content of speech is the same important as the voiceprint. This paper proposes an effective speech content protection method by constructing a frame-by-frame adversarial speech generation system. We revisited the adversarial examples generating method in the recent machine learning field and selected the phonetic state sequence of sensitive speech for the adversarial examples generation. We build an adversarial speech collection. Moreover, based on the speech collection, we proposed a neural network-based frame-by-frame mapping method to recover the speech content by converting from the adversarial speech to the human speech. Experiment shows our proposed method can encode and recover any sensitive audio, and our method is easy to be conducted with publicly available resources of speech recognition technology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-adversarial">
<titleInfo>
<title>Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianying</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the advent of the General Data Protection Regulation (GDPR) and increasing privacy concerns, the sharing of speech data is faced with significant challenges. Protecting the sensitive content of speech is the same important as the voiceprint. This paper proposes an effective speech content protection method by constructing a frame-by-frame adversarial speech generation system. We revisited the adversarial examples generating method in the recent machine learning field and selected the phonetic state sequence of sensitive speech for the adversarial examples generation. We build an adversarial speech collection. Moreover, based on the speech collection, we proposed a neural network-based frame-by-frame mapping method to recover the speech content by converting from the adversarial speech to the human speech. Experiment shows our proposed method can encode and recover any sensitive audio, and our method is easy to be conducted with publicly available resources of speech recognition technology.</abstract>
<identifier type="citekey">li-etal-2022-adversarial</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.792</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7291</start>
<end>7297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection
%A Li, Sheng
%A Li, Jiyi
%A Liu, Qianying
%A Gong, Zhuo
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F li-etal-2022-adversarial
%X With the advent of the General Data Protection Regulation (GDPR) and increasing privacy concerns, the sharing of speech data is faced with significant challenges. Protecting the sensitive content of speech is the same important as the voiceprint. This paper proposes an effective speech content protection method by constructing a frame-by-frame adversarial speech generation system. We revisited the adversarial examples generating method in the recent machine learning field and selected the phonetic state sequence of sensitive speech for the adversarial examples generation. We build an adversarial speech collection. Moreover, based on the speech collection, we proposed a neural network-based frame-by-frame mapping method to recover the speech content by converting from the adversarial speech to the human speech. Experiment shows our proposed method can encode and recover any sensitive audio, and our method is easy to be conducted with publicly available resources of speech recognition technology.
%U https://aclanthology.org/2022.lrec-1.792
%P 7291-7297
Markdown (Informal)
[Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection](https://aclanthology.org/2022.lrec-1.792) (Li et al., LREC 2022)
ACL