
An automatic classification task involving 44 speakers was performed using convolutional neural networks (CNN) on broadband spectrograms extracted from 2-second sequences of a spontaneous speech corpus (NCCFr)
Author(s) -
Cédric Gendrot,
Emmanuel Ferragne,
Thomas Pellegrini
Publication year - 2020
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - spectrogram , convolutional neural network , computer science , speech recognition , task (project management) , broadband , artificial intelligence , natural language processing , telecommunications , engineering , systems engineering