TY - GEN
T1 - Birdvox-Full-Night
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
AU - Lostanlen, Vincent
AU - Salamon, Justin
AU - Farnsworth, Andrew
AU - Kelling, Steve
AU - Bello, Juan Pablo
N1 - Funding Information:
This work is partially supported by NSF awards 1633259 and 1633206, Leon Levy Foundation, and a Google faculty award.
Funding Information:
This work is partially supported by NSF awards 1633259 and 1633206
PY - 2018/9/10
Y1 - 2018/9/10
N2 - This article addresses the automatic detection of vocal, nocturnally migrating birds from a network of acoustic sensors. Thus far, owing to the lack of annotated continuous recordings, existing methods had been benchmarked in a binary classification setting (presence vs. absence). Instead, with the aim of comparing them in event detection, we release BirdVox-full-night, a dataset of 62 hours of audio comprising 35402 flight calls of nocturnally migrating birds, as recorded from 6 sensors. We find a large performance gap between energy-based detection functions and data-driven machine listening. The best model is a deep convolutional neural network trained with data augmentation. We correlate recall with the density of flight calls over time and frequency and identify the main causes of false alarm.
AB - This article addresses the automatic detection of vocal, nocturnally migrating birds from a network of acoustic sensors. Thus far, owing to the lack of annotated continuous recordings, existing methods had been benchmarked in a binary classification setting (presence vs. absence). Instead, with the aim of comparing them in event detection, we release BirdVox-full-night, a dataset of 62 hours of audio comprising 35402 flight calls of nocturnally migrating birds, as recorded from 6 sensors. We find a large performance gap between energy-based detection functions and data-driven machine listening. The best model is a deep convolutional neural network trained with data augmentation. We correlate recall with the density of flight calls over time and frequency and identify the main causes of false alarm.
KW - Acoustic signal detection
KW - Audio databases
KW - Ecosystems
KW - Multi-layer neural network
KW - Supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85052394269&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052394269&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8461410
DO - 10.1109/ICASSP.2018.8461410
M3 - Conference contribution
AN - SCOPUS:85052394269
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 266
EP - 270
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 April 2018 through 20 April 2018
ER -