The endpoint detection of cough signal in continuous speech / 生物医学工程学杂志
Journal of Biomedical Engineering
;
(6): 544-555, 2010.
Artículo
en Chino
| WPRIM
| ID: wpr-230834
ABSTRACT
The endpoint detection of cough signal in continuous speech has been researched in order to improve the efficiency and veracity of manual recognition or computer-based automatic recognition. First, using the short time zero crossing ratio(ZCR) for identifying the suspicious coughs and getting the threshold of short time energy based on acoustic characteristics of cough. Then, the short time energy is combined with short time ZCR in order to implement the endpoint detection of cough in continuous speech. To evaluate the effect of the method, first, the virtual number of coughs in each recording was identified by two experienced doctors using the graphical user interface (GUI). Second, the recordings were analyzed by automatic endpoint detection program under Matlab7.0. Finally, the comparison between these two results showed The error rate of undetected cough is 2.18%, and 98.13% of noise, silence and speech were removed. The way of setting short time energy threshold is robust. The endpoint detection program can remove most speech and noise, thus maintaining a lower rate of error.
Texto completo:
Disponible
Índice:
WPRIM (Pacífico Occidental)
Asunto principal:
Sonido
/
Algoritmos
/
Procesamiento de Señales Asistido por Computador
/
Reconocimiento de Normas Patrones Automatizadas
/
Inteligencia Artificial
/
Tos
/
Determinación de Punto Final
/
Métodos
Tipo de estudio:
Estudio diagnóstico
/
Estudio pronóstico
Límite:
Humanos
Idioma:
Chino
Revista:
Journal of Biomedical Engineering
Año:
2010
Tipo del documento:
Artículo
Similares
MEDLINE
...
LILACS
LIS