This paper addresses a problem belonging to the domain of whale audio processing, more specifically the automatic classification of sounds produced by the Mysticete species. The specific task is quite challenging given the vast repertoire of the involved species, the adverse acoustic conditions, and the nearly non-existent prior scientific work. Two feature sets coming from different domains (frequency and wavelet) were designed to tackle the problem. These are modeled by an Echo State Network classifier. The data set includes five species (. Blue, Fin, Bowhead, Southern Right, and Humpback) and it is publicly available at http://www.mobysound.org/. We followed a thorough experimental procedure and achieved more than satisfactory recognition rates.
Deep Learning Framework for Classifying Sounds of Mysticete Whales / S. Ntalampiras - In: Handbook of Neural Computation / [a cura di] P. Samui, S. Sekhar, V.E. Balas. - [s.l] : Elsevier, 2017. - ISBN 9780128113189. - pp. 403-415 [10.1016/B978-0-12-811318-9.00022-3]
Deep Learning Framework for Classifying Sounds of Mysticete Whales
S. Ntalampiras
2017
Abstract
This paper addresses a problem belonging to the domain of whale audio processing, more specifically the automatic classification of sounds produced by the Mysticete species. The specific task is quite challenging given the vast repertoire of the involved species, the adverse acoustic conditions, and the nearly non-existent prior scientific work. Two feature sets coming from different domains (frequency and wavelet) were designed to tackle the problem. These are modeled by an Echo State Network classifier. The data set includes five species (. Blue, Fin, Bowhead, Southern Right, and Humpback) and it is publicly available at http://www.mobysound.org/. We followed a thorough experimental procedure and achieved more than satisfactory recognition rates.File | Dimensione | Formato | |
---|---|---|---|
07 whale_elsevierBook.pdf
accesso aperto
Tipologia:
Pre-print (manoscritto inviato all'editore)
Dimensione
444.59 kB
Formato
Adobe PDF
|
444.59 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.