Audio fingerprint parameterization for multimedia advertising identification

Medina Cartuche, Jose Luis; Vega Zamora, Oswaldo Francisco; Mendoza Siguenza, Daniel Emilio; Saquicela Galarza, Victor Hugo; Espinoza Mejia, Jorge Mauricio

Por favor, use este identificador para citar o enlazar este ítem: http://dspace.ucuenca.edu.ec/handle/123456789/33304

Título :	Audio fingerprint parameterization for multimedia advertising identification
Autor:	Medina Cartuche, Jose Luis Vega Zamora, Oswaldo Francisco Mendoza Siguenza, Daniel Emilio Saquicela Galarza, Victor Hugo Espinoza Mejia, Jorge Mauricio
Palabras clave :	Advertising Monitoring Audio Fingerprint Automatic Content Recognition Signal Processing
Área de conocimiento FRASCATI amplio:	1. Ciencias Naturales y Exactas
Área de conocimiento FRASCATI detallado:	1.2.1 Ciencias de la Computación
Área de conocimiento FRASCATI específico:	1.2 Informática y Ciencias de la Información
Área de conocimiento UNESCO amplio:	06 - Información y Comunicación (TIC)
ÁArea de conocimiento UNESCO detallado:	0613 - Software y Desarrollo y Análisis de Aplicativos
Área de conocimiento UNESCO específico:	061 - Información y Comunicación (TIC)
Fecha de publicación :	2017
Fecha de fin de embargo:	31-dic-2050
Volumen:	volumen 2017
Fuente:	IEEE Second Ecuador Technical Chapters Meeting (ETCM)
metadata.dc.identifier.doi:	10.1109/ETCM.2017.8247498
Editor:	Institute of Electrical and Electronics Engineers Inc.
Ciudad:	SALINAS
Tipo:	ARTÍCULO DE CONFERENCIA
Abstract:	This article follows step by step a general framework for fingerprint extraction in order to develop a system for advertisements' monitoring. The parameterization process uses some spatial and spectral characteristics measured over 600 advertisements that contain various types of sounds. Key factors such as accuracy, process time, and granularity are analyzed together in order to enhance the system performance. At the end, the algorithm shows an accuracy of 99% using three seconds of granularity samples, and also the best compromise between processing time and performance is achieved. This study suggests a set of parameterization steps which could be successfully implemented in other related audio applications. © 2017 IEEE.
Resumen :	This article follows step by step a general framework for fingerprint extraction in order to develop a system for advertisements' monitoring. The parameterization process uses some spatial and spectral characteristics measured over 600 advertisements that contain various types of sounds. Key factors such as accuracy, process time, and granularity are analyzed together in order to enhance the system performance. At the end, the algorithm shows an accuracy of 99% using three seconds of granularity samples, and also the best compromise between processing time and performance is achieved. This study suggests a set of parameterization steps which could be successfully implemented in other related audio applications. © 2017 IEEE.
URI :	http://dspace.ucuenca.edu.ec/handle/123456789/33304 https://ieeexplore.ieee.org/document/8247498
URI Fuente:	https://ieeexplore.ieee.org/Xplore/home.jsp
ISBN :	978-153863894-1
ISSN :	0000-0000
Aparece en las colecciones:	Artículos

Ficheros en este ítem:

Fichero	Descripción	Tamaño	Formato
documento.pdf Until 2050-12-31	document	593.24 kB	Adobe PDF	Visualizar/Abrir Solicitar una copia

Este ítem está protegido por copyright original

Mostrar el registro Dublin Core completo del ítem

Centro de Documentacion Regional "Juan Bautista Vázquez"

Biblioteca Campus Central		Biblioteca Campus Salud		Biblioteca Campus Yanuncay
Av. 12 de Abril y Calle Agustín Cueva, Telf: 4051000 Ext. 1311, 1312, 1313, 1314. Horario de atención: Lunes-Viernes: 07H00-21H00. Sábados: 08H00-12H00		Av. El Paraíso 3-52, detrás del Hospital Regional "Vicente Corral Moscoso", Telf: 4051000 Ext. 3144. Horario de atención: Lunes-Viernes: 07H00-19H00		Av. 12 de Octubre y Diego de Tapia, antiguo Colegio Orientalista, Telf: 4051000 Ext. 3535 2810706 Ext. 116. Horario de atención: Lunes-Viernes: 07H30-19H00