Large scale gender representation analysis in French TV and radio is presented, based on automatic information extraction procedures: speech time (1 million hours of programs), number of oral references to characters (588 hours) and visual exposition time (588 hours).

A convolutional neural network (CNN) based architecture is proposed for MIREX 2018 music and speech detection challenge. The system uses log-mel filterbank features. It has 4 convolutional and 4 dense layers. It is part of the inaSpeechSegmenter open-source framework, which was designed for conducting gender equality studies.