Brij Mohan Lal Srivastava

Co-founder and CEO of Nijta

Nijta SAS


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.


  • Speech & Language Processing
  • Neural Networks
  • Privacy


  • 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

Recent Experience


Research Engineer

Microsoft Research India

Mar 2018 – Sep 2018 Bengaluru
Worked on end-to-end code-switched speech recognition for Hindi-English language pair.

Research Intern

Microsoft Research India

Jul 2017 – Mar 2018 Bengaluru
Proposed phone and homophone merging methods for code-switched speech recognition.

Recent & Upcoming Talks

Speaker Anonymization -- Representation, Evaluation and Formal Guarantees

PhD thesis defense

Recent approaches towards Speaker Anonymization

Summary of my research progress towards speaker anonymization in 2019 and 2020 for biometric community.

Privacy in Speech Processing

General directions towards privacy in speech processing, aimed for masters and PhD students.

Recent Publications

Quickly discover relevant content by filtering publications.

Differentially Private Speaker Anonymization

Challenged the previous disentanglement assumption in feature extraction process, by removing residual speaker information from …

A comparative study of speech anonymization metrics

We compare three different metrics (EER, Cllr and Linkability) for measuring privacy in speaker anonymization algorithms. Interesting …

Design Choices for X-vector Based Speaker Anonymization

We investigate the effect of various design choices in x-vector based speaker anonymization method, on Privacy and Utility. Some …