Deep Learning

Informations segmentales pour la caractérisation phonétique du locuteur : variabilité inter- et intra-locuteurs

Nous avons effectué une classification automatique de 44 locuteurs à partir de réseaux de neurones convolutifs (CNN) sur la base de spectrogrammes à bandes larges calculés sur des séquences de 2 secondes extraites d’un corpus de parole spontanée …

Caractérisation du locuteur par CNN à l’aide des contours d’intensité et d’intonation : comparaison avec le spectrogramme

Dans ce travail nous avons recours aux variations de f0 et d’intensité de 44 locuteurs francophones à partir de séquences de 4 secondes de parole spontanée pour comprendre comment les paramètres prosodiques peuvent être utilisés pour caractériser des …

Données COVID-19

Quelques visualisations

Ridi, Pagliaccio !

Neural style transfer for videos.

The contribution of lip protrusion to Anglo-English /r/: Evidence from hyper- and non-hyperarticulated speech

Articulatory variation of /r/ has been widely observed in rhotic varieties of English, particularly with regards to tongue body shapes, which range from retroflex to bunched. However, little is known about the production of /r/ in modern non-rhotic …

The contribution of lip protrusion to Anglo-English /r/: Evidence from hyper- and non-hyperarticulated speech

Here in my deep purple dreams

On the deep learning approach to phonetics: black boxes?

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 recognize 45 speakers with a deep convolutional neural network (CNN). The same network was also trained with 62 …

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 /ɑ̃/ Although the model achieved fairly high accuracy – over 85 % – our primary focus here was phonetic …

Deep learning and voice comparison : phonetically-motivated vs. automatically-learned features