{"id":1662,"count":3,"description":"Nuestro grupo desarrolla actividades científicas y tecnológicas en reconocimiento automático de habla, identificación y verificación de locutores, segmentación automática de habla en locutores, reconocimiento de idioma, comprensión de lenguaje natural, conversión texto a habla con emociones, sistemas avanzados de diálogo persona-máquina en entornos inteligentes, sistemas de traducción entre lenguas, con amplia experiencia en la traducción de voz a LSE y aplicaciones de ayudas a personas con limitaciones.\n \nLas principales líneas de investigación<\/strong> son:\n\nReconocimiento del habla\nComprensión de habla\nReconocimiento de locutores\nSistemas de diálogo persona-máquina\nAnálisis de habla con emociones\nAplicaciones de Tecnología del Habla en entornos inteligentes\nConversión texto-habla\n","link":"https:\/\/www.upm.es\/recursosidi\/en\/map\/en_speech-and-machine-learning-technology-group\/","name":"Speech and Machine Learning Technology Group","slug":"en_speech-and-machine-learning-technology-group","taxonomy":"donde","parent":0,"meta":[],"id_grupo_portal":"258","acronimo":"Grupo THAU","resumen":"

\n Our group consists of 17 members of the Higher Technical School of Telecommunications Engineers (HTSET) and belongs to the Electronic Engineering Department <\/a>(DIE).<\/span>\n <\/p>","imagen":false,"responsable":"Jos\u00e9 Manuel Pardo Mu\u00f1oz","lineas":"Analysis and synthesis of emotional speech \nLanguage recognition\nMan-machine Dialogue Systems \nSpeaker recognition\nSpeech Recognition\nSpeech Technology Applications in Intelligent Environments\nSpeech understanding \nText-to-speech conversion","direccion":"","telefono":"9106 72223","pagina_web":"https:\/\/blogs.upm.es\/gthau\/","email":"gi.gthau@upm.es","actividades":"

\n We have collaborated with various national and international companies, such as Speech Plus, Digital Equipment Corporation, Telia Promotor Infovox, Hewlett Packard and Dygra and marketed several systems based on the technology developed in the group. We have also integrated tool and systems designed by us into business environments, showing the capacity for technology transfer.<\/span>\n <\/p>\n

\n Moreover, we have taken part in several European (ESPRIT, LRE, LE, TIDE, IST), national and regional projects relating to our field of research, using the most advanced equipment and tools to develop speech technology.<\/span>\n <\/p>","contenido":"","pictures":"http:\/\/www.upm.es\/observatorio\/vi\/gestor_general\/recuperar_archivo.jsp?id=1733\rhttp:\/\/www.upm.es\/observatorio\/vi\/gestor_general\/recuperar_archivo.jsp?id=1180\rhttp:\/\/www.upm.es\/observatorio\/vi\/gestor_general\/recuperar_archivo.jsp?id=1734","descripcion":"

\n Our group carried out scientific and technological work on automatic speech recognition, identification and verification of speakers, automatic speech segmentation, language recognition, understanding natural language, conversion of text to speech with emotion, advanced systems for person-machine dialogue in smart environments, language translation systems, with extensive experience in voice to Spanish sign language translation, and applications to help people with limitations.\n <\/p>\n

\n The main lines of research<\/strong> are as follows:\n <\/p>\n