Recent Publications

More Publications

Notre recherche examine l’effet du Lee Silverman Voice Treatment (LSVT LOUD®) sur l’aire et la position de l’espace vocalique, la …

Nous avons effectué une classification automatique de 44 locuteurs à partir de réseaux de neurones convolutifs (CNN) sur la base de …

Dans ce travail nous avons recours aux variations de f0 et d’intensité de 44 locuteurs francophones à partir de séquences de 4 secondes …

Hearing swear words or taboo words causes us discomfort. Research suggests that emotional responses caused by such words are stronger …

OBJECTIVE: Interference suppression and response inhibition are distinct effortful inhibitory processes. Yet they rely on partly …

Broadband spectrograms of French vowels /ɑ̃/, /a/, /ɛ/, /e/, /i/, /ə/, and /ɔ/ extracted from radio broadcast corpora were used to …

Drawing from Trudgill’s finding that some American phonetic features are common in British pop-songs, this paper explores whether …

A deep convolutional neural network was trained to classify 45 speakers based on spectrograms of their productions of the French vowel …

Like every late L2 - learner, French native speakers are characterized by a foreign accent. The literature emphasizes that the vowels / …

Recent & Upcoming Talks

Somebody’s pronunciation says a lot about who they are: this observation does not only apply to speaking; it also holds true for …

Invited keynote at PAC 2019.

Recent Posts

More Posts

Why should I die?

Quelques visualisations

Searching Youtube comments.

Some musicians’ names with counterintuitive pronunciations.

Neural style transfer for videos.



EEGino Pi

Low-cost EEG for research

CminR Praatik

Praat and R code for a doctoral seminar I teach at Université Paris Diderot.


Forensic Voice Comparison

Lab Monitor

An IoT project to monitor the use of resources in our phonetics lab.

Ohbot Opera

The Ohbot Pi - a programmable robot head - lip-syncs to opera arias.


A super useful software program to record speech corpora.