Files and links (2)
A Convolutional Neural Network Bird Species Recognizer Built From Little Data by Iteratively Training, Detecting, and Labeling1.80 MB
Published VersionCC BY V4.0, Open Access
Journal article
A Convolutional Neural Network Bird Species Recognizer Built From Little Data by Iteratively Training, Detecting, and Labeling
Frontiers in Ecology and Evolution, Vol.10, pp.1-11
2022
Abstract
Automatically detecting the calls of species of interest in audio recordings is a common but often challenging exercise in ecoacoustics. This challenge is increasingly being tackled with deep neural networks that generally require a rich set of training data. Often, the available training data might not be from the same geographical region as the study area and so may contain important differences. This mismatch in training and deployment datasets can impact the accuracy at deployment, mainly due to confusing sounds absent from the training data generating false positives, as well as some variation in call types. We have developed a multiclass convolutional neural network classifier for seven target bird species to track presence absence of these species over time in cotton growing regions. We started with no training data from cotton regions but we did have an unbalanced library of calls from other locations. Due to the relative scarcity of calls in recordings from cotton regions, manually scanning and labeling the recordings was prohibitively time consuming. In this paper we describe our process of overcoming this data mismatch to develop a recognizer that performs well on the cotton recordings for most classes. The recognizer was trained on recordings from outside the cotton regions and then applied to unlabeled cotton recordings. Based on the resulting outputs a verification set was chosen to be manually tagged and incorporated in the training set. By iterating this process, we were gradually able to build the training set of cotton audio examples. Through this process, we were able to increase the average class F1 score (the harmonic mean of precision and recall) of the recognizer on target recordings from 0.45 in the first iteration to 0.74.
Details
- Title
- A Convolutional Neural Network Bird Species Recognizer Built From Little Data by Iteratively Training, Detecting, and Labeling
- Authors
- Philip Eichinski (Author) - Queensland University of TechnologyCallan Alexander (Author) - Queensland University of TechnologyPaul Roe (Author) - Queensland Univ Technol, Fac Sci, Sch Comp Sci, Brisbane, Qld, AustraliaStuart Parsons (Author) - Queensland University of TechnologySusan Fuller (Author) - Queensland University of Technology
- Publication details
- Frontiers in Ecology and Evolution, Vol.10, pp.1-11
- Publisher
- Frontiers Research Foundation
- Date published
- 2022
- DOI
- 10.3389/fevo.2022.810330
- ISSN
- 2296-701X
- Copyright note
- Copyright © 2022 Eichinski, Alexander, Roe, Parsons and Fuller. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
- Organisation Unit
- University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 99677998702621
- Output Type
- Journal article
Metrics
17 File views/ downloads
162 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Web Of Science research areas
- Ecology
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites