{"id":25550,"date":"2022-01-11T10:52:41","date_gmt":"2022-01-11T09:52:41","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=25550"},"modified":"2022-03-01T09:40:40","modified_gmt":"2022-03-01T08:40:40","slug":"privacy-preserving-speech-representation-learning-using-vector-quantization","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/privacy-preserving-speech-representation-learning-using-vector-quantization\/","title":{"rendered":"Privacy-Preserving Speech Representation Learning using Vector Quantization"},"content":{"rendered":"

Seminar from Pierre Champion, Phd student at INRIA of Nancy and LIUM<\/h2>\n

 <\/p>\n

Date:<\/strong> 14\/01\/2022
\nTime:<\/strong> 11h00
\nLocalization:<\/strong> IC2 Boardroom, online<\/a>
\nSpeaker:<\/strong> Pierre Champion<\/a><\/p>\n

 <\/p>\n

Privacy-Preserving Speech Representation Learning using Vector Quantization <\/strong><\/p>\n

 <\/p>\n

Speech signals are a rich source of speaker-related information, including sensitive attributes like gender, identity, etc. Those sensitive attributes can be extracted and used for malicious purposes like voice spoofing. Despite the inherent sensitivity of speech signals, more and more services, mainly virtual assistants like Apple\u2019s Siri, Google Now, Microsoft\u2019s Cortana, or Amazon\u2019s Alexa, process, collect and store personal speech signal in centralized servers raising severe privacy concerns.<\/p>\n

The main focus of my work is the investigation of anonymization techniques to remove sensitive attributes from speech signals while preserving the linguistic content. In this seminar, I will present my latest approaches that anonymize the hidden bottleneck representation of an ASR system so that it cannot be used to identify speakers. The method is based on Vector Quantization, whose primary goal is to generate a compressed discrete representation of the input data. I will present how Vector Quantization can learn private representation, show the results, and discuss future directions.<\/p><\/div><\/div><\/div><\/div>

 <\/div>
 <\/div>
 <\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"

Seminar from Pierre Champion, Phd student at INRIA of Nancy and LIUM   Date: 14\/01\/2022 Time: 11h00 Localization: IC2 Boardroom, online Speaker: Pierre Champion   Privacy-Preserving Speech Representation Learning using Vector Quantization   Speech signals are a rich source of speaker-related information, including sensitive attributes like gender, identity, etc. Those sensitive attributes can be extracted […]<\/p>\n

READ MORE<\/span><\/i><\/span><\/a><\/p>\n","protected":false},"author":14,"featured_media":13238,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[43],"tags":[49],"acf":[],"_links":{"self":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/25550"}],"collection":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/comments?post=25550"}],"version-history":[{"count":0,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/25550\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media\/13238"}],"wp:attachment":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media?parent=25550"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/categories?post=25550"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/tags?post=25550"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}