Claire Pillot-Loiseau

Learn More
This paper presents an early version of an open extendable research and educational platform to support users in learning and mastering the different types of rare-singing. The platform is interfaced with a portable helmet to synchronously capture multiple signals during singing in a non-laboratory environment. Collected signals reflect articulatory(More)
The article proposes a real-time technique for visualizing tongue motion driven by ultrasound image sequences. Local feature description is used to follow characteristic speckle patterns in a set of mid-sagittal contour points in an ultrasound image sequence, which are then used as markers for describing movements of the tongue. A 3D tongue model is(More)
The human beatbox is the art of reproducing all types of sounds with the mouth while 'adapting' them for better control. To understand how these 'voice virtuosos' juggle with so many different sounds--instrumental, rhythmic, and vocal--at the same time, we have performed a descriptive analysis of three beatboxers by observing their vocal tract behaviour by(More)
This paper presents the rationale, objectives and advances of an ongoing project that aims to characterize the acoustic-phonetic features of French dysarthric speech, covering a large amount of patients and three dysarthria types. The two French corpora of dysarthric patients used for the selection of the speech data are described, as well as the design of(More)
This article intends to study the influence of two parameters (language and speech task) on the manifestation of creaky voice among six American women learning French. The speakers were recorded in both reading and spontaneous conditions, in English and French. These languages were chosen for their difference at the phonatory level. The number of creaky(More)
Les résultats acoustiques montrent que [ɑ̃ , ɛ̃ , ɔ̃ ], sont plus longues que [a, ɛ, o] chez tous les locuteurs et plus particulièrement chez les locutrices bosniaques. Les données quantitatives à partir du signal RMS (Root Mean Square) de l'accéléromètre piezoélectrique ne montrent pas de différences notoires entre les deux populations en ce qui concerne :(More)
This article reports the results of a multiparametrical analysis of Mongolian Long Song, characterised by multiple ornamentation and shows the similarities between the laryngeal behaviour observed during these ornamentations and the compensatory gesture produced by patients after supracricoid partial laryngectomy. This study includes (1) a physiological(More)
Silent Speech Interfaces have been proposed for communication in silent conditions or as a new means of restoring the voice of persons who have undergone a laryngectomy. To operate such a device, the user must articulate silently. Isolated word recognition tests performed with fixed and portable ultrasound based silent speech interface equipment show that(More)
  • 1