Latest: With the support of Inria and Euratechnologies, I have decided to take voice anonymization to society at large in the form of Nijta, a deeptech startup based in Lille. If you are interested to know more and try the solutions provided by Nijta, send me an email at the address given at the end of this page, and I promise to contact you soon.
I recently finished my PhD at Inria where I worked in the Magnet and the Multispeech teams. I was supervised by Dr. Aurélien Bellet, Dr. Emmanuel Vincent and Prof. Marc Tommasi. My work mainly focused towards privacy-preserving speech processing.
Check out the Voice Privacy Challenge to know more about the privacy benchmarks we obtained using our baseline and participate to evaluate your own anonymization methods.
PhD in Computer Science, 2018 - 2021
Inria (Université de Lille)
MS by Research in Computer Science, 2014 - 2017
International Institute of Information Technology (IIIT), Hyderabad
BTech in Information Technology, 2007 - 2011
SASTRA University
Challenged the previous disentanglement assumption in feature extraction process, by removing residual speaker information from speaker-independent attributes (linguistic and prosodic features). The removal is achieved by adding differentially-private noise in these features, which allows us to provide formal provable guarantees of privacy leakage.
We investigate the effect of various design choices in x-vector based speaker anonymization method, on Privacy and Utility. Some choices seem to be more robust than others in VoicePrivacy challenge setup.
We aim a paradigm shift in context of speaker privacy evaluation from “security by obscurity” to Semi-Informed and Informed attackers. We show that privacy obtained by voice transformation techniques can be breached by an informed attacker.
In this work, we propose a privacy-preserving framework based on speaker-adversarial training of end-to-end ASR. We evaluate the system using closed-set and open-set identification and observe a strange disparity in results.
In this work, we propose a large scale spoken language identification technique over 176 languages. We also provide evidence that the languages are clustered based on their geographical and ethnological proximity.