The 2015 Signal Separation Evaluation Campaign

Abstract : In this paper, we report the 2015 community-based Signal Separation Evaluation Campaign (SiSEC 2015). This SiSEC consists of four speech and music datasets including two new datasets: " Professionally produced music recordings " and " Asynchronous recordings of speech mixtures ". Focusing on them, we overview the campaign specifications such as the tasks, datasets and evaluation criteria. We also summarize the performance of the submitted systems.
Type de document :
Communication dans un congrès
International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Aug 2015, Liberec, France. Lecture Notes in Computer Science, 9237, pp.387-395, 2015, Latent Variable Analysis and Signal Separation. 〈10.1007/978-3-319-22482-4_45〉
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01188725
Contributeur : Antoine Liutkus <>
Soumis le : lundi 31 août 2015 - 14:19:36
Dernière modification le : jeudi 5 avril 2018 - 18:30:02
Document(s) archivé(s) le : mardi 1 décembre 2015 - 10:29:19

Fichier

LVA-ICA2015_055_original_v1.pd...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Nobutaka Ono, Zafar Rafii, Daichi Kitamura, Nobutaka Ito, Antoine Liutkus. The 2015 Signal Separation Evaluation Campaign. International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Aug 2015, Liberec, France. Lecture Notes in Computer Science, 9237, pp.387-395, 2015, Latent Variable Analysis and Signal Separation. 〈10.1007/978-3-319-22482-4_45〉. 〈hal-01188725〉

Partager

Métriques

Consultations de la notice

323

Téléchargements de fichiers

905