Secondment of Heydi Méndez VázquezFrom CENATAV to Le Mans Université

From September 18, 2024 to December 14, 2024

Le Mans Université is proud to host our colleague Heydi Méndez Vázquez visiting from La Havane, Cuba, for 3 months.

Biometric matching is the process of verifying a person’s identity based on the person’s unique biological or behavioral characteristics. Common biometric traits or modalities include face, voice, fingerprint, iris scans, and others.

Multimodal biometric matching takes advantage of multiple types of data simultaneously, while compensating or addressing the limitations that individual modalities may have on their own.  Such approach has shown to be superior not only in accuracy, but also in reliability.

The main goals of the proposed research are:

1. To study and analyse state-of-the-art methods that combine face and voice information.
2. To study and obtain existing benchmark databases containing both modalities.
3. To propose a method for biometric identification and/or deep fake detection combining face and voice descriptors.
4. Evaluation of the proposal on benchmark databases.
5. To write a first draft of a paper with the obtained results.