Identificación automática de características cualitativas del llanto infantil

In infant cry analysis, the identification of qualitative characteristics is of great importance, because this provides additional information that allows to identify variations and similarities between normal and pathological cries. Nowadays, the analysis of qualitative characteristics is made manu...

ver descrição completa

Detalhes bibliográficos
Autor: MARÍA ANTONIA RUÍZ DÍAZ
Formato: tesis de maestría
Estado:Versión aceptada para publicación
Fecha de publicación:2011
País:México
Recursos:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositorio:Repositorio Institucional del INAOE
Idioma:español
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/722
Acesso em linha:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/722
Access Level:acceso abierto
Palavra-chave:info:eu-repo/classification/Procesamiento de la señal/Signal processing
info:eu-repo/classification/Reconocimiento de patrones/Pattern recognition
info:eu-repo/classification/Procesamiento de señal acústica/Acoustic signal processing
info:eu-repo/classification/Reconocimiento de voz/Speech recognition
info:eu-repo/classification/Análisis del llanto/Cry analysis
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/12
info:eu-repo/classification/cti/1203
Descrição
Resumo:In infant cry analysis, the identification of qualitative characteristics is of great importance, because this provides additional information that allows to identify variations and similarities between normal and pathological cries. Nowadays, the analysis of qualitative characteristics is made manually, through visual (spectrogram) and auditive (sound) perception of medical experts, they make a diagnosis according to what they see and hear. In this work, we present a method based in the use of a threshold, this threshold is applied to the energy of the signal, our method allows detect automatically cry units of a record, and another threshold, which eliminates the inspiratory segments. Also we present the dodecagram method, which allows identify the type of melody, shifts, glides, and noise concentrations reasonably in cry units automatically. Finally, in accordance to the qualitative characteristics found, the method automatically provides a diagnosis of the analyzed cry, which can be: normal cry or cry with a pathological tendency.