Emmanuel Ferragne
Emmanuel Ferragne
Home
Publications
Talks
Posts
Projects
Resources for PhD and masters students
Light
Dark
Automatic
Forensic
Automatic classification of phonation types in spontaneous speech: towards a new workflow for the characterization of speakers' voice quality
Voice quality is known to be an important factor for the characterization of a speaker’s voice, both in terms of physiological features …
Anaïs Chanclu
,
Imen Ben Amor
,
Cédric Gendrot
,
Emmanuel Ferragne
,
Jean-Francois Bonastre
PDF
Cite
Project
DOI
Spot the difference
Don’t blame it on the CSI effect; we too glamourize science!
Emmanuel Ferragne
Last updated on Mar 21, 2023
8 min read
VoCSI-Telly
VoCSI-Telly: Voice and Crime Scene Investigators on Telly
The CSI effect
On the perception of forensic science.
Emmanuel Ferragne
Last updated on Mar 21, 2023
3 min read
Deep learning and voice comparison: phonetically-motivated vs. automatically-learned features
Broadband spectrograms of French vowels /ɑ̃/, /a/, /ɛ/, /e/, /i/, /ə/, and /ɔ/ extracted from radio broadcast corpora were used to …
Cédric Gendrot
,
Emmanuel Ferragne
,
Thomas Pellegrini
PDF
Cite
Project
Towards phonetic interpretability in deep learning applied to voice comparison
A deep convolutional neural network was trained to classify 45 speakers based on spectrograms of their productions of the French vowel …
Emmanuel Ferragne
,
Cédric Gendrot
,
Thomas Pellegrini
PDF
Cite
Project
VoxCrim
Forensic Voice Comparison
«
Cite
×