AN OPEN-SOURCE SPEAKER GENDER DETECTION FRAMEWORK FOR MONITORING GENDER EQUALITY

David Doukhan (1) , Jean Carrive (2) , Félicien Vallet (2) , Anthony Larcher (3) , Sylvain Meignier (3)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 INA - Institut National de l'Audiovisuel
3 LIUM - Laboratoire d'Informatique de l'Université du Mans

This paper presents an approach based on acoustic analysis to describe gender equality in French audiovisual streams, through the estimation of male and female speaking time. Gender detection systems based on Gaussian Mixture Models , i-vectors and Convolutional Neural Networks (CNN) were trained using an internal database of 2,284 French speakers and evaluated using REPERE challenge corpus. The CNN system obtained the best performance with a frame-level gender detection F-measure of 96.52 and a hourly gender speaking time percentage error bellow 0.6%. It was considered reliable enough to realize large-scale gender equality descriptions. The proposed gender detection system has been packaged as an open-source framework.

Mots clés: Digital Humanities; Speech Gender De-tection; Convolutional Neural Network; i-vector

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

David Doukhan, Jean Carrive, Félicien Vallet, Anthony Larcher, Sylvain Meignier. AN OPEN-SOURCE SPEAKER GENDER DETECTION FRAMEWORK FOR MONITORING GENDER EQUALITY. IEEE International Conference on Acoustic Speech and Signal Processing, Apr 2018, Calgary, Canada. ⟨hal-01927560⟩