Observatorio de I+D+i UPM

Descripción
New tools based on speech analysis can improve and accelerate diagnosis of Parkinson's disease. In this work, the use of some specific segments of speech, around the so called Acoustic Landamarks, are used with different families of features such as acoustic cues or Rasta-PLP and GMM-UBM-Blend classification methods to detect Parkinson's disease. Results of 87% are obtained. Burst segmentes provide the most relevant information when detecting Parkinson's disease whjile GMM-UMB-Blend is revealed as a promising techinique when using small databases and segmented speech.
Internacional	Si
Nombre congreso	10th International Workshop Models and Analysis of Vocal Emissions for Biomedical Applications
Tipo de participación	960
Lugar del congreso
Revisores	Si
ISBN o ISSN	978-88-6453-607-1
DOI
Fecha inicio congreso	13/12/2017
Fecha fin congreso	15/12/2017
Desde la página	73
Hasta la página	76
Título de las actas	Models and Analysis of Vocal Emissions for Biomedical Applications: 10th Internation Workshop

Esta actividad pertenece a memorias de investigación

• Autor: Laureano Moro Velazquez (UPM)
• Autor: Jorge Andres Gomez Garcia (UPM)
• Autor: Juan Ignacio Godino Llorente (UPM)
• Autor: Jesús Villalba (John Hopkins University)
• Autor: Najim Dehak (John Hopkins University)

• Creador: Grupo de Investigación: Informática Aplicada al Procesado de Señal e Imagen
• Departamento: Teoría de la Señal y Comunicaciones (Provisional)