Low Resource Species Agnostic Bird Activity Detection

  title={Low Resource Species Agnostic Bird Activity Detection},
  author={Mark Anderson and John Kennedy and Naomi Harte},
  journal={2021 IEEE Workshop on Signal Processing Systems (SiPS)},
This paper explores low resource classifiers and features for the detection of bird activity, suitable for embedded Automatic Recording Units which are typically deployed for long term remote monitoring of bird populations. Features include low-level spectral parameters, statistical moments on pitch samples, and features derived from amplitude modulation. Performance is evaluated on several lightweight classifiers using the NIPS4Bplus dataset. Our experiments show that random forest classifiers… 
1 Citations

Figures and Tables from this paper



Advances in Automatic Bird Species Recognition from Environmental Audio

The state-of-art development in automated bird species recognition is reviewed, wide range of algorithms on noise removal, bird call detection, feature extraction for classification are identified, and significant software tools and publicly available datasets for the task are presented.

Automated bird acoustic event detection and robust species classification

Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning

This work introduces a technique for feature learning from large volumes of bird sound recordings, inspired by techniques that have proven useful in other domains, and demonstrates that unsupervised feature learning provides a substantial boost over MFCCs and Mel spectra without adding computational complexity after the model has been trained.

Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection challenge

Results from a collaborative data challenge showed that general‐purpose acoustic bird detection can achieve very high retrieval rates in remote monitoring data, with no manual recalibration, and no pretraining of the detector for the target species or the acoustic conditions in the target environment.

Convolutional Neural Networks for Large-Scale Bird Song Classification in Noisy Environment

A convolutional neural network based deep learning approach for bird song classification that was used in an audio record-based bird identification challenge, called BirdCLEF 2016, and reached a MAP score of over 40% for main species and over 33% formain species mixed with background species.

Two convolutional neural networks for bird detection in audio signals

Two approaches to detect the presence of bird calls in audio recordings using convolutional neural networks on mel spectrograms are presented and it is found that despite very different architectures, both approaches can be tuned to perform equally well.

Bird Species Recognition Using Support Vector Machines

  • S. Fagerlund
  • Computer Science
    EURASIP J. Adv. Signal Process.
  • 2007
Automatic identification of bird species by their vocalization is studied and results with the proposed method suggest better or equal performance when compared to existing reference methods.

Automatic detection of bird species from audio field recordings using HMM-based modelling of frequency tracks

An automatic system for detection of bird species in field recordings using a sinusoidal detection algorithm to segment the acoustic scene into isolated spectro-temporal segments, represented as a temporal sequence of frequencies of the detected sinusoid, referred to as frequency track.

Comparison of audio recording system performance for detecting and monitoring songbirds

Acoustic recording systems are being used more frequently to estimate habitat occupancy or relative abundance, and to monitor population trends over time. A potential concern with digital recording

NIPS4Bplus: a richly annotated birdsong audio dataset

NIPS4Bplus is presented, the first richly annotated birdsong audio dataset, that is comprised of recordings containing bird vocalisations along with their active species tags plus the temporal annotations acquired for them.