TU Darmstadt / ULB / TUbiblio

Learning multi-labeled bioacoustic samples with an unsupervised feature learning approach

Loza Mencía, Eneldo and Nam, Jinseok and Lee, Dong-Hyun
Glotin, H. and LeCun, Y. and Mallat, Stéphane and Tchernichovski, Ofer and Artières, Thierry and Halkias, Xanadu (eds.) (2013):
Learning multi-labeled bioacoustic samples with an unsupervised feature learning approach.
In: Proceedings of Neural Information Scaled for Bioacoustics, from Neurons to Big Data, ISSN 979-10-90821-04-0,
[Online-Edition: http://www.ke.tu-darmstadt.de/publications/papers/lozanam201...],
[Conference or Workshop Item]

Abstract

Multi-label Bird Species Classification competition provides an excellent oppor- tunity to analyze the effectiveness of acoustic processing and mutlilabel learning. We propose an unsupervised feature extraction and generation approach based on latest advances in deep neural network learning, which can be applied generically to acoustic data. With state-of-the-art approaches from multilabel learning, we achieved top positions in the competition, only surpassed by teams with profound expertise in acoustic data processing.

Item Type: Conference or Workshop Item
Erschienen: 2013
Editors: Glotin, H. and LeCun, Y. and Mallat, Stéphane and Tchernichovski, Ofer and Artières, Thierry and Halkias, Xanadu
Creators: Loza Mencía, Eneldo and Nam, Jinseok and Lee, Dong-Hyun
Title: Learning multi-labeled bioacoustic samples with an unsupervised feature learning approach
Language: English
Abstract:

Multi-label Bird Species Classification competition provides an excellent oppor- tunity to analyze the effectiveness of acoustic processing and mutlilabel learning. We propose an unsupervised feature extraction and generation approach based on latest advances in deep neural network learning, which can be applied generically to acoustic data. With state-of-the-art approaches from multilabel learning, we achieved top positions in the competition, only surpassed by teams with profound expertise in acoustic data processing.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Knowl­edge En­gi­neer­ing
Event Title: Proceedings of Neural Information Scaled for Bioacoustics, from Neurons to Big Data
Date Deposited: 25 Nov 2015 08:51
Official URL: http://www.ke.tu-darmstadt.de/publications/papers/lozanam201...
Export:

Optionen (nur für Redakteure)

View Item View Item