Albayzín-2014 evaluation: audio segmentation and classification in broadcast news domains: audio segmentation and classification in broadcast news domains

Diego Castán, David Tavarez, Paula Lopez-Otero, Javier Franco-Pedroso, Héctor Delgado, Eva Navas, Laura Docio-Fernández, Daniel Ramos, Javier Serrano, Alfonso Ortega, Eduardo Lleida

Producció científica: Contribució a una revistaArticleRecercaAvaluat per experts

18 Cites (Scopus)

Resum

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 originalEnglish
Número d’article33
Pàgines (de-a)1-9
Nombre de pàgines9
RevistaEurasip Journal on Audio, Speech, and Music Processing
Volum2015
Número1
DOIs
Estat de la publicacióPublicada - 1 de des. 2015

Fingerprint

Navegar pels temes de recerca de 'Albayzín-2014 evaluation: audio segmentation and classification in broadcast news domains: audio segmentation and classification in broadcast news domains'. Junts formen un fingerprint únic.

Com citar-ho