Welcome
Research activity
Virtual speaker
Teaching activity
Curriculum vitae
Personal

 

Research

Interests

Computer Vision
Human Computer Interaction
Multimodal signal processing
Multimodal Interfaces
Talking heads

Ph.D.

I have successfully defended my Ph.D. about Personalizable Realistic Audiovisual Synthesis, which involves all my previous showed interests and has obtained the VIII Rosina Ribalta first award. If you want to discuss any matter about this subject, please, email me! I will be happy to be hearing from you!

Demos

Here you can see some demos about my current research work.

Try PREVIS, our first text-to-audiovisual synthesizer on-line!

Visual synthesis of sign language.
Audiovisual synthesis of a singing avatar.
Audiovisual Catalan virtual speaker.
Audiovisual synthesis of an english sentence.
Audiovisual synthesis of a catalan sentence.
Visual synthesis of changing emotional expressions. Try to guess the original and synthetic ones!!
Learnt appearance of a real person. Try to guess the original face and the learnt one!!
Learnt appearance of another real person. Try to guess!!
Learnt appearance of a third person. Guess the original and the learnt ones!!
Face tracking with slow movements.
Face tracking with fast movements and appearance changes.
Preliminar experiments about tracking with a cylindrical mesh (based on the work of Jing Xiao)

Some of these videos may need the divx codec or the windows media player. Get them here:

Research Projects

“SAVE” (TEC2006-08043/TCM), funded by the Spanish Science and Technology Council.

“IntegraTV-4all” (FIT-350301-2004-2), funded by the Spanish Science and Technology Council.

“Virtual characters” (RDITSCON04), funded by the Centre d’Innovació i Desenvolupament Empresarial (CIDEM).

“Virtual speaker for natural interaction” (FIT-340100-2004-20), funded by the Spanish Science and Technology Council.

“Videophone” (FIT-350300-2004-44), funded by the Spanish Science and Technology Council.

“Virtual Characters” (RDITSCON04), funded by the Centre d’Innovació i Desenvolupament Empresarial (CIDEM).

“Detección de estados incipientes de somnolencia en conductors de vehículos a motor” (DPI2002-02279), funded by the Spanish Science and Technology Council.

“Virtual Speaker” (FIT-150500-2002-410), funded by the Spanish Science and Technology Council.

“Automatic detection of driver drowsiness” (FIT-1101100-2002-77), funded by the Spanish Science and Technology Council.

“Automatic analysis of industrial paint coatings through computer vision” (FIT-070000-2002-115), funded by the Spanish Science and Technology Council.

Publications

J. Melenchón, J. Simó, G. Cobo, E. Martínez, Objective Viseme Extraction and Audiovisual Uncertainty: Estimation Limits between Auditory and Visual Modes, to appear in International Conference on Auditory-Visual Speech Processing, 2007, Hilvarenbeek, (The Netherlands).

J. Melenchón, E. Martínez, Efficiently Downdating, Composing and Splitting Singular Value Decompositions Preserving the Mean Information, to appear in Iberian Conference on Pattern Recognition and Image Analysis, LNCS 4478:436-443, 2007, Girona (Spain).- PDF -

X. Sevillano, J. Melenchón, J.C. Socoró, Análisis y Síntesis Audiovisual para Interfaces Multimodales Ordenador-Persona, VII Congreso Internacional de Interacción Persona-Ordenador, 2006, Puertollano (Spain).

J. Melenchón, I. Iriondo, L. Meler, Simultaneous and Causal Appearance Learning and Tracking , Electronic Letters on Computer Vision and Image Analysis 5(3):44-54, 2005, Barcelona (Spain). - PDF -

J. Melenchón, L. Meler, I. Iriondo, On-the-fly Training, Lecture Notes in Computer Science Third International Workshop on Articulated Motion and Deformable Objects, 2004, Palma de Mallorca (Spain). - PDF Second best paper award -

Ignasi Iriondo, Francesc Alías, Javier Melenchón, M. Angeles Llorca Modeling and Synthesizing Emotional Speech for Catalan Text-to-Speech Synthesis, Lecture Notes in Computer Science Tutorial and Research Workshop on Affective Dialog Systems, ADS04, 2004, Kloster Irsee (Germany).

A. Arañó, J.Melenchón, Compresión en tiempo real para síntesis audiovisual, URSI, 2004, Barcelona (Spain).

J. Melenchón, I. Iriondo, J.C. Socoró, E. Martínez, L. Meler, Lip Animation of a Personalizad Facial Model from Auditory Speech, IEEE Internacional Symposium on Signal Processing and Information Technology (ISSPIT), diciembre 2003, Darmstat (Germany). - PDF -

J. Gonzalvo, J.A. Morán, J.Melenchón, Detección del ángulo de llegada con un array microfónico, URSI, 2003, La Coruña (Spain).

X. Quintana, E. Martínez, J. Melenchón, Automatic evaluation of degradation of paint coatings through EM algorithm, IEEE International Conference on Image Processing (ICIP), setiembre 2003, Barcelona (Spain).

J. Melenchón, F. De la Torre, I. Iriondo, F. Alías, E. Martínez, Ll. Vicent, Text to visual synthesis with appearance models, IEEE International Conference on Image Processing (ICIP), setiembre 2003, Barcelona (Spain). - PDF -

I. Iriondo, F. Alías, J. Sanchis, J. Melenchón, A Hybrid Method Oriented to Concatenative Text-to-Speech Síntesis, the 8th European Conference on Speech Communication and Technology (EUROSPEECH), setiembre 2003, Ginebra (Switzerland).

I. Iriondo, F. Alías, J. Melenchón, Un modelo híbrido orientado a la síntesis multimodal del habla, SEPLN, setiembre 2002, Valladolid (España).

J. Melenchón, I. Iriondo, F. Alías, Modelo 2D parametrizado basado en imágenes reales orientado a síntesis de cabezas parlantes, URSI, setiembre 2002, Alcalá de Henares (España).

J. Melenchón, F. Alías, I. Iriondo, PREVIS: A Person-Specific Realistic Virtual Speaker, IEEE international Conference on Multimedia and Expo (ICME), agosto 2002, Lausanne (Suiza). - PDF -

F. De la Torre, J. Vitria, P. Radeva, J. Melenchón, EigenFiltering for Flexible Eigentracking, 15th International Conference on Pattern Recognition (ICPR), setiembre 2000, Barcelona (España).

back to top