Browsing by Author "Melenchón Maldonado, Javier"
Now showing items 1-5 of 5
-
A Hybrid Method Oriented to Concatenative Text-to-Speech Synthesis
Iriondo Sanz, Ignasi; Alías Pujol, Francesc; Sanchís Bernabeu, Francisco Javier; Melenchón Maldonado, Javier (2003-09-01)In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This ... -
Análisis y Síntesis Audiovisual para Interfaces Multimodales Ordenador-Persona
Sevillano Domínguez, Xavier; Melenchón Maldonado, Javier; Socoró Carrié, Joan Claudi (2006-11)Las técnicas multimodales de procesamiento de señal están llamadas a jugar un papel preponderante en la implementación de interfaces que faciliten la interacción natural entre los ordenadores y los ... -
Un modelo híbrido orientado a la síntesis multimodal del habla
Iriondo Sanz, Ignasi; Alías Pujol, Francesc; Melenchón Maldonado, Javier (Procesamiento del lenguaje natural, No. 29 (2002), 2002)En este articulo se presenta un sistema de conversión texto-habla de alta calidad utilizando voz segmentada en difonemas y trifonemas. El sistema de síntesis implementado se basa en un modelo híbrido ... -
Objective Viseme Extraction and Audiovisual Uncertainty: Estimation Limits between Auditory and Visual Modes
Melenchón Maldonado, Javier; Simó, Jordi; Cobo Rodríguez, Germán; Martínez Marroquín, Elisa (2007-08)An objective way to obtain consonant visemes for any given Spanish speaking person is proposed. Its face is recorded while speaking a balanced set of sentences and stored as an audiovisual sequence. ... -
Simultaneous and causal appearance learning and tracking
Melenchón Maldonado, Javier; Iriondo Sanz, Ignasi; Meler Corretjé, Lourdes (Electronic letters on computer vision and image analysis, Vol. 5, No 3 (2005), 2005-08)A novel way to learn and track simultaneously the appearance of a previously non-seen face without intrusive techniques can be found in this article. The presented approach has a causal behaviour: no ...