| Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach. | |
| | |
MedLine Citation:
|
PMID: 22712937 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H. J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning. |
| | |
Authors:
|
Forrest Briggs; Balaji Lakshminarayanan; Lawrence Neal; Xiaoli Z Fern; Raviv Raich; Sarah J K Hadley; Adam S Hadley; Matthew G Betts |
Related Documents
:
|
22612767 - How decisions emerge: action dynamics in intertemporal decision making. 22718317 - Computational modeling of the human atrial anatomy and electrophysiology. 22019767 - Consensus among flexible fitting approaches improves the interpretation of cryo-em data. 22876167 - Interplay between the localization and kinetics of phosphorylation in flagellar pole de... 16402597 - Analysis of heartbeat dynamics by point process adaptive filtering. 16477427 - Stone analysis. |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: The Journal of the Acoustical Society of America Volume: 131 ISSN: 1520-8524 ISO Abbreviation: J. Acoust. Soc. Am. Publication Date: 2012 Jun |
Date Detail:
|
Created Date: 2012-06-20 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 7503051 Medline TA: J Acoust Soc Am Country: United States |
Other Details:
|
Languages: eng Pagination: 4640-50 Citation Subset: IM |
Affiliation:
|
Department of Electrical Engineering & Computer Science, Oregon State University, Corvallis, Oregon 97331. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Spatial correlation in the ambient core noise field of a turbofan engine.
Next Document: Characterizing fundamental frequency in Mandarin: A functional principal component approach utilizin...