Title: Recent Approaches of Speaker Anonymization Techniques
Date and Place: November 17th 14h00, Citi (room TBD) + visio
Speaker: Dr. Mohamed Maouche (Postdoc Inria)
An increasing number of smart devices embed speech-commands. The usage of speech offers simplicity, accessibility and it also opens new human-computer interactions. However, the gathering and exploitation of this type of data raise many privacy threats as speech data is sensitive in nature. Personal information about the speaker can be inferred (e.g., gender, emotion…). In addition, speech is a biometric characteristic, it can be used to identify speakers. To address this issue anonymization techniques have been proposed. In this talk, we are going to present the recent approaches for speech anonymization techniques with a focus on x-vector based anonymization.
Starting October 2021, I’m a post-doc in Privatics (Inria) at Lyon working on privacy in Federated Learning in the Chaire DSVD supported by Renault and Labex IMU. Previously, I was a post-doc with Magnet (Inria) at Lille for two years, working on speech privacy. Before, I have received my Ph.D. in 2019 from Insa Lyon which I did under the supervision of Sara Bouchenak and Sonia Ben Mokhtar in Liris Lab working on Location Privacy. My main interest throughout my research is the re-identification and anonymization problem, especially while facing peculiar data.