|
NOMBRE
|
DESCRIPCIÓN
|
RESPONSABLE
|
|
Grupo de Tecnologías Multimedia (GTM)
|
Reconocimiento y síntesis de habla multilingüe, desarrollo de sistemas de diálogo, detección de estado emocional y de salud
|
Carmen García Mateo
|
|
Grupo de Trabajo en Tecnologías Software (GTTS)
|
Desarrollo de tecnologías para (1) procesamiento del habla (transcripción automática, reconocimiento y verificación del locutor, verificación y reconocimiento de la lengua, etc.) y (2) extracción de información de recursos con habla.
|
Germán Bordel García
|
|
Ingeniería de Lenguaje Natural y Reconocimiento de Formas (ELiRF)
|
El grupo ELiRF pertenece al Instituto VRAIN (Valencian Research Institute for Artificial Intelligence) de la Universidad Politécnica de Valencia. Sus líneas de investigación se centran en el reconocimiento y comprensión del habla, sistemas de diálogo, análisis de sentimientos, y resumen automático.
|
Lluis Hurtado i Oliver
|
|
Laboratorio de Ingeniería Biomédica
|
El grupo tiene las siguientes líneas de investigación: Algoritmos de análisis de datos/parámetros fisiológicos, Aceleración de aplicaciones con hardware específico, Anotación de metabolitos, Tecnologías de rehabilitación y apoyo la discapacidad, y Realidad virtual y aumentada aplicadas a la salud
|
Javier Tejedor Noguerales
|
|
Pattern Recognition and Human Language Technologies Research Center (PRHLT)
|
The PRHLT center was founded in 2013 by several researchers that had started their research activities in speech processing and pattern recognition in the 1980s. The PRHLT center keeps research lines related to speech processing, natural language processing, deep learning, machine translation, handwritten text processing, and computer vision. These areas are reflected in applications such as multimodal interaction, multimodal signal processing, document analysis, information extraction, medical applications, and social media analysis.
|
Carlos D. Martínez Hinarejos
|
|
Research group on Media Technologies (GTM)
|
The Research Group on Media Technologies (GTM) aims at a more natural interaction between human beings, machines and their environment, through the research in the fields of Acoustics, Signal processing and Interaction. Human-computer interaction (HCI) comprises an input (human to machine) and an output (machine to human) channel. As for the former, we work on speech and speaker recognition, the analysis of gestures and expressions on different modalities (image, voice, text, and their combination), and the identification of audio events to adapt the interaction to the environment and the user. Moreover, we investigate on vibroacoustics and architectural acoustics to guarantee the acoustic comfort and intelligibility in the context of interaction. Regarding the output channel, we focus on the generation of voice by numerically simulating its underlying physics, and by resorting to speech synthesis approaches as well (text-to-speech and voice transformation). Also we develop virtual characters (avatars) with natural movements (animations from MoCap), and work on the analysis and organization of multimedia data. In what concerns HCI interfaces, we inspect new paradigms of interaction through smart objects, human-robot interaction (HRI), and emphatic user experience (UX). Finally, we also investigate on parametric array technology to generate audible sound from non-linear propagation of modulated ultrasonic beams.
|
Francesc Alías Pujol
|
|
Signal Processing, Multimedia Transmission and Speech/Audio Technologies (SigMAT)
|
SigMAT was formally created in 2012, although its members have been involved in research on signal and speech processing since 1988. It is composed of faculty members and researchers from the dept of Signal Theory, Networking and Communications of the University of Granada as well as other external researchers from the industry. Currently, the group is involved in several projects related to the development of new statistical signal processing and deep learning techniques applied to several problems. In particular, the interests of the SIGMAT Group are mainly (but not only) focused on the following topics: (1) Research, innovation and development of speech technologies: speech enhancement, recognition, coding, synthesis (silent and thought speech) and biometrics (speaker recognition and antispoofing). (2) Development of robust transmission techniques of multimedia information: speech, images, video. (3) Research in other fields of signal processing application, such as array signal processing (beamforming), ultrasonics or proteomics.
|
Antonio M. Peinado Herreros
|
|
SISDIAL - Sistemas de Diálogo Hablado y Multimodal
|
El grupo centra su actividad en el análisis, diseño y desarrollo de sistemas de diálogo, prestando especial atención a las siguientes cuestiones: Reconocimiento, comprensión y generación de habla; Gestión del diálogo; Simulación de usuarios; Reconocimiento de emociones; Interacción en ambientes de Inteligencia Ambiental (AmI); Generación de modelos de personalidad para el ordenador.
|
Zoraida Callejas Carrión y David Griol Barres
|
|
Speech Interactive Research Group (SPIN) - Universidad del País Vasco/Euskal Herriko Unibertsitatea
|
The Speech Interactive Research Group was formed in 1990 as the research group on pattern recognition and speech technology of the University of the Basque Country. Its central focus has been for a long time the development of techniques for automatic speech recognition, understanding and translation based on learning methods. We have also been involved in the development of spoken dialog systems, where we aimed at developing interactive interfaces adapted to the task and to the user as well as at learning from human interaction. We now also investigate the emotional aspects of interaction, focusing on the emotion detection from the analysis of speech signal as well as from the dialogic language in social media. The group has, therefore, a wide experience in both basic research and technology transfer in these areas.
|
M. Inés Torres Barañano
|
|
Voice Input Voice Output Laboratory (ViVoLab)
|
ViVoLab aims at producing transformative breakthroughs in fields ranging from speech technologies, language & audio processing, and applied machine learning. Our research is focused on automatic speech recognition, natural language processing, speaker diarization, verification and identification, acoustic event detection and classification, speech enhancement and audio quality assessment. In addition, we are interested in the use of speech and language technologies for the assessment of communication disorders, and technology development for the analysis and retrieval of audiovisual content, multimodal person and events recognition and multimedia content summarization.
|
Eduardo Lleida Solano
|
 -[1]- -[2]- |
Mostrando resultados [11 - 20] de un total de 20 resultados en la página 2 sobre un total de 2 páginas |
