PROTAX-Sound : A probabilistic framework for automated animal sound identification

Show full item record



Permalink

http://hdl.handle.net/10138/224420

Citation

de Camargo , U M , Somervuo , P & Ovaskainen , O 2017 , ' PROTAX-Sound : A probabilistic framework for automated animal sound identification ' , PLoS One , vol. 12 , no. 9 , 0184048 . https://doi.org/10.1371/journal.pone.0184048

Title: PROTAX-Sound : A probabilistic framework for automated animal sound identification
Author: de Camargo, Ulisses Moliterno; Somervuo, Panu; Ovaskainen, Otso
Contributor: University of Helsinki, Biosciences
University of Helsinki, Biosciences
University of Helsinki, Biosciences
Date: 2017-09-01
Language: eng
Number of pages: 15
Belongs to series: PLoS One
ISSN: 1932-6203
URI: http://hdl.handle.net/10138/224420
Abstract: Autonomous audio recording is stimulating new field in bioacoustics, with a great promise for conducting cost-effective species surveys. One major current challenge is the lack of reliable classifiers capable of multi-species identification. We present PROTAX-Sound, a statistical framework to perform probabilistic classification of animal sounds. PROTAX-Sound is based on a multinomial regression model, and it can utilize as predictors any kind of sound features or classifications produced by other existing algorithms. PROTAX-Sound combines audio and image processing techniques to scan environmental audio files. It identifies regions of interest (a segment of the audio file that contains a vocalization to be classified), extracts acoustic features from them and compares with samples in a reference database. The output of PROTAX-Sound is the probabilistic classification of each vocalization, including the possibility that it represents species not present in the reference database. We demonstrate the performance of PROTAX-Sound by classifying audio from a species-rich case study of tropical birds. The best performing classifier achieved 68% classification accuracy for 200 bird species. PROTAX-Sound improves the classification power of current techniques by combining information from multiple classifiers in a manner that yields calibrated classification probabilities.
Subject: RAIN-FOREST
CLASSIFICATION
COMMUNITY
RECOGNITION
RECORDINGS
MODELS
BIRDS
1181 Ecology, evolutionary biology
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
de_Camargo_et_al_2017.pdf 2.206Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record