Papers by jihene serkhane
Http Www Theses Fr, 2005
L'exploration vocale et l'imitation orofaciale sont vraisemblablement necessaires au deve... more L'exploration vocale et l'imitation orofaciale sont vraisemblablement necessaires au developpement de la production verbale. Une revue de questions transdisciplinaire sur l'imitation nous a permis de proposer de nouvelles hypotheses sur la co-structuration des domaines perceptif et moteur dan~ l'emergence de la production de la parole ambiante. Pour simuler de maniere realiste l'imitation et l'exploration, un agent sensorimoteur a ete concu a base de modeles computationnels de la production de la parole dans un conduit vocal en croissance, de sa perception audio-visuo-somesthesique, et de l'apprentissage de liens entre ses domaines articulatoire et perceptif. Par cette plate-forme experimentale virtuelle, le processus d'exploration a ete simule avant (a 4 mois) et au debut (a 7mois) du babillage, celui d'imitation l'a ete a 4 mois. Dans le premier cas, nous avons cherche a estimer, dans une analyse par modelisation, les capacites articulatoires des nourrissons d'apres des mesures acoustiques decrivant leurs vocalisations, et tester des hypotheses formulees dans le domaine de la parole sur le developpement precoce du controle du systeme articulatoire. L'imitation a ete implementee sous la forme d'un modele probabiliste qui apprend des elements issus de l'espace d'exploration estime a 4 mois. La carte des liens perceptionproduction qui en resulte a ete utilisee pour simuler une experience (tiree de la litterature) sur l'imitation precoce de voyelles [i a u]. Nous avons cherche a reproduire les performances accomplies par les nourrissons, pour interroger les caracteristiques de la carte cognitive et de l'apprentissage potentiellement en jeu dans ce comportement.
Proceedings of the 14th annual ACM international conference on Multimedia - MULTIMEDIA '06, 2006
While there have been great advances in quantification of the genotype of organisms, including fu... more While there have been great advances in quantification of the genotype of organisms, including full genomes for many species, the quantification of phenotype is at a comparatively primitive stage. Part of the reason is technical difficulty: the phenotype covers a wide range of characteristics, ranging from static morphological features, to dynamic behavior. The latter poses challenges that are in the area of multimedia signal processing. Automated analysis of video and audio recordings of animal and human behavior is a growing area of research, ranging from the behavioral phenotyping of genetically modified mice or drosophila to the study of song learning in birds and speech acquisition in human infants. This paper reviews recent advances and identifies key problems for a range of behavior experiments that use audio and video recording. This research area offers both research challenges and an application domain for advanced multimedia signal processing. There are a number of MMSP tools that now exist which are directly relevant for behavioral quantification, such as speech recognition, video analysis and more recently, wired and wireless sensor networks for surveillance. The research challenge is to adapt these tools and to develop new ones required for studying human and animal behavior in a high throughput manner while minimizing human intervention. In contrast with consumer applications, in the research arena there is less of a penalty for computational complexity, so that algorithmic quality can be maximized through the utilization of larger computational resources that are available to the biomedical researcher.
ABSTRACT In order to accurately follow the growth of the vocal tract and the speech articulators ... more ABSTRACT In order to accurately follow the growth of the vocal tract and the speech articulators and to infer their motor control and acoustic potentialities, it is essential to have anatomic and physiologic data throughout ontogenesis, from gestation to adulthood The morphogenesis of the vocal tract, which involves the bony structures, their development, and cranio-facial growth during ontogenesis, is far from linear. The new data provided by genetics hell) interpreting the process of bony growth and thus of vocal tract reshaping from fetus to adult, To predict the consequences (if vocal tract growth on the first speech productions (proto-vocalic and proto-consonantal articulations, babbling), anthropomorphic articulatory, models are developed based on articulatory, data. The articulatory models can generate realistic acoustic stimuli, which enable the testing of hypotheses about adult and newborn perceptuo-motor processes. These articulatory models can provide phylogenetical cues to the debate around the emergence of speech. The stuck of vocal tract growth therefore constitutes a key experimental paradigm for speech research.
… on Spoken Language …, 2002
Page 1. MOTOR SPECIFICATIONS OF A BABY ROBOT VIA THE ANALYSIS OF INFANTS&#x27... more Page 1. MOTOR SPECIFICATIONS OF A BABY ROBOT VIA THE ANALYSIS OF INFANTS' VOCALIZATIONS J. Serkhane (1), JL Schwartz(1), LJ Boë(1), B. Davis(2), C. Matyear(2) (1) Institut de la Communication Parlée, CNRS ...
Interaction Studies, 2005
Speech is a perceptuo-motor system. A natural computational modeling framework is provided by cog... more Speech is a perceptuo-motor system. A natural computational modeling framework is provided by cognitive robotics, or more precisely speech robotics, which is also based on embodiment, multimodality, development, and interaction. This paper describes the bases of a virtual baby robot which consists in an articulatory model that integrates the non-uniform growth of the vocal tract, a set of sensors, and a learning model. The articulatory model delivers sagittal contour, lip shape and acoustic formants from seven input parameters that characterize the configurations of the jaw, the tongue, the lips and the larynx. To simulate the growth of the vocal tract from birth to adulthood, a process modifies the longitudinal dimension of the vocal tract shape as a function of age. The auditory system of the robot comprises a “phasic” system for event detection over time, and a “tonic” system to track formants. The model of visual perception specifies the basic lips characteristics: height, width...
Revue française de linguistique appliquée, 2008
La croissance de l'instrument vocal : contrôle, modélisation, potentialités acoustiques et conséq... more La croissance de l'instrument vocal : contrôle, modélisation, potentialités acoustiques et conséquences perceptives
Uploads
Papers by jihene serkhane