Albayzín-2014 evaluation: audio segmentation and classification in broadcast news domains
Resumen: Audio segmentation is important as a pre-processing task to improve the performance of many speech technology tasks and, therefore, it has an undoubted research interest. This paper describes the database, the metric, the systems and the results for the Albayzín-2014 audio segmentation campaign. In contrast to previous evaluations where the task was the segmentation of non-overlapping classes, Albayzín-2014 evaluation proposes the delimitation of the presence of speech, music and/or noise that can be found simultaneously. The database used in the evaluation was created by fusing different media and noises in order to increase the difficulty of the task. Seven segmentation systems from four different research groups were evaluated and combined. Their experimental results were analyzed and compared with the aim of providing a benchmark and showing up the promising directions in this field.
Idioma: Inglés
DOI: 10.1186/s13636-015-0076-3
Año: 2015
Publicado en: EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2015, 33 (2015), [9 pp.]
ISSN: 1687-4714

Factor impacto JCR: 0.797 (2015)
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 175 / 255 = 0.686 (2015) - Q3 - T3
Categ. JCR: ACOUSTICS rank: 21 / 30 = 0.7 (2015) - Q3 - T3

Factor impacto SCIMAGO:

Financiación: info:eu-repo/grantAgreement/ES/MINECO-FEDER/TEC2012-38939-C03
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2011-28169-C05-02
Tipo y forma: Article (Published version)
Área (Departamento): Teoría de la Señal y Comunicaciones (Departamento de Ingeniería Electrónica y Comunicaciones)
Exportado de SIDERAL (2017-12-11-14:02:29)

Este artículo se encuentra en las siguientes colecciones:
articulos > articulos-por-area > teoria_de_la_senal_y_comunicaciones



 Notice créée le 2017-06-12, modifiée le 2017-12-11


Versión publicada:
 PDF
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)