LIP6 CNRS Sorbonne Université Tremplin Carnot Interfaces
Direct Link LIP6 » News » PhD students

RADENEN Mathieu

PhD graduated
Team : MLIA
Departure date : 10/01/2014
Supervision : Thierry ARTIÈRES

Markovian Contextual Models

Modeling time series has practical applications in many domains : speech, gesture and handwriting recognition, synthesis of realistic character animations etc... The starting point of our modeling is that an important part of the variability between observation sequences may be the consequence of a few contextual variables that remain fixed all along a sequence or that vary slowly with time. For instance a sentence may be uttered quite differently according to the speaker emotion, a gesture may have more amplitude depending on the height of the performer etc... Such a variability cannot always be removed through preprocessing.
We first propose the generative framework of Contextual Hidden Markov Models (CHMM) to model directly the influence of contextual information on observation sequences by parameterizing the probability distributions of HMMs with static or dynamic contextual variables. We test various instances of this framework on classification of handwritten characters, speech recognition and synthesis of eyebrow motion from speech for a virtual avatar. For each of these tasks, we investigate in what extent such modeling can translate into performance gains.
We then introduce a natural and efficient way to exploit contextual information into Contextual Hidden Conditional Random Fields (CHCRF), the discriminative counter part of CHMMs. CHCRF may be viewed as an efficient way to learn a HCRF that exploit contextual information.
Finally, to learn from fewer examples, we propose a Transfer Learning approach using Contextual HMMs. This method relies on sharing information between classes where classic generative models train independent class models.
Defence : 09/30/2014 - 10h - Site Jussieu 25-26/105
Jury members :
M. LINARES Georges-Université d'Avignon et des Payes de Vaucluse [Rapporteur]
M. HEUTTE Laurent-Laboratoire LITIS, UFR des Sciences, Université de Rouen [Rapporteur]
LIKFORMAN-SULEM Laurence-TELECOM ParisTech
ACHARD Catherine-ISIR Paris 6
BECHET Frédéric-Laboratoire d'Informatique Fondamentale Marseille
ARTIERES Thierry-LIP6, Paris 6

2012-2014 Publications

 Mentions légales
Site map |