Context Some experiments made on automatic video summarization showed that the costume feature is one of the most significant clue for the identification of keyframes belonging to some given excerpts. This property is mainly justified by the fact that costumes are attached to the character function in the video document.The approach proposed here consists first in characterizing the region located
Context Prosodic features carry a substantial part of the language identity that may be sufficient for humans to perceptually identify some languages. Among these supra-segmental features, intonation is very promising both for linguistic and automatic processing purposes. However, intonation modelling is difficult, both in terms of theoretical definition and automatic processing. We propose here some prosodic modelling approaches that bring
Context The objective of the feature extraction step is to capture the most relevant and discriminate characteristics of the signal to recognize. Although characters in the same class have some variances due to different spoken styles for different users, there must exist some consistencies. That is why feature extraction is needed and those features extracted are put into a classifier.
Project N°: FP6-507752 Schedule March 2004- February 2008 Objectives MUSCLE is an EC-sponsored Network of Excellence that aims at establishing and fostering closer collaboration between research groups in multimedia datamining and machine learning. The Network integrates the expertise of over forty research groups working on image and video processing, speech and text analysis, statistics and machine learning. The goal is
MathSTIC CNRS Specific Action Schedule 2002 Consortium MIP People involved in SAMOVA team Philippe Joly Régine André-Obrecht
Phonologie du Français Contemporain Collaboration Schedule 2002 Collaboration with ERSS Web site PFC project People involved in SAMOVA team Régine André-Obrecht Jérôme Farinas
STIC CNRS Specific Action Schedule 2002 Consortium LABRI IRISA INRIA Rocquencourt IRCCYN LiP6 People involved in SAMOVA team Philippe Joly
RIAM project Schedule 2002-2004 Objectives The goal of the project is to build a general and open framework allowing the easy development of applications for editing interactive video documents. Consortium CS INA Canal+ Technologies Arte France Vecsys IRISA (Texmex and Vista teams) People involved in SAMOVA team Philippe Joly Julien Pinquier Régine André-Obrecht
Automatic Retrieval of Audio & Speech Informations (RAIVES) CNRS project Schedule 2002-2003 Abstract (in french) Les documents sonores font à l’heure actuelle partie de ce que l’on appelle le « web invisible ». Le projet a pour objectif une structuration de ces documents sonores, en particulier radiophoniques, à partir de l’indexation par leur contenu, de manière à leur donner un sens du
Project ITEA Schedule 2002-2004 Objectives KLIMT, addresses the need for greater intelligence in a distributed multimedia environment. It resulted in the delivery of a multimedia content processing platform with a service-oriented architecture. Consortium THALES (F) Zanussi (I) LiP6 (F) Meta4 (E) 4ème Millénaire (F) Isoft (F) Sinequa (F) Softeco Sismat (I) TTS (I) I&IMS (E) B-kin (E) ESI (E) UMPC (F) Eurécom (F) Politecnico di Milano (I) People involved in SAMOVA team Philippe Joly Isabelle