You are here

Time-frequency segmentation of bird song in noisy acoustic environments

TitleTime-frequency segmentation of bird song in noisy acoustic environments
Publication TypeConference Paper
Year of Publication2011
AuthorsNeal, L., F. Briggs, R. Raich, and X. Z. Fern
Conference Name2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Pagination2012 - 2015
Date Published05/2011
Conference LocationPrague, Czech Republic
ISBN Number978-1-4577-0538-0
Keywordsaudio segmentation, bird species identification, time-frequency segmentation

Recent work in machine learning considers the problem of identifying bird species from an audio recording. Most methods require segmentation to isolate each syllable of bird call in input audio. Energy-based time-domain segmentation has been successfully applied to low-noise, single-bird recordings. However, audio from automated field recorders contains too much noise for such methods, so a more robust segmentation method is required. We propose a supervised time frequency audio segmentation method using a Random Forest classifier, to extract syllables of bird call from a noisy signal. When applied to a test data set of 625 field-collected audio segments, our method isolates 93.6% of the acoustic energy of bird song with a false positive rate of 8.6%, outperforming energy thresholding.