Archivio Istituzionale della RicercaA hierarchical spatio-temporal model that infers the latent spectral shape from a set of bio-acoustic signals by means of the Nearest neighbour Gaussian process is proposed. The model aims to account for the effects of the relative relationship between time and the spectral shape of the recorded vocalizations and that of time discretization. The goal is to obtain a representative model of the inherent acoustic structure of the species.
A Hierarchical Spatio-Temporal Model for Time-Frequency Data: An application in bioacoustic analysis / Mastrantonio, Gianluca; Bibbona, Enrico; Yip, Hiu Ching; Daria, Valente; Marco, Gamba. - ELETTRONICO. - (2023), pp. 673-678. (Intervento presentato al convegno SIS 2023 - Statistical Learning, Sustainability and Impact Evaluation tenutosi a Ancona (ITA) nel 21/06/2023-23/06/2023).
A Hierarchical Spatio-Temporal Model for Time-Frequency Data: An application in bioacoustic analysis
Gianluca Mastrantonio;Bibbona Enrico;Yip Hiu Ching;
2023
Abstract
A hierarchical spatio-temporal model that infers the latent spectral shape from a set of bio-acoustic signals by means of the Nearest neighbour Gaussian process is proposed. The model aims to account for the effects of the relative relationship between time and the spectral shape of the recorded vocalizations and that of time discretization. The goal is to obtain a representative model of the inherent acoustic structure of the species.
| File | Dimensione | Formato | |
|---|---|---|---|
|
short-paper-sis-2023.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
1.04 MB
Formato
Adobe PDF
|
1.04 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/3004126