Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach.

By Forrest Briggs, Balaji Lakshminarayanan, Lawrence Neal, Xiaoli Z. Fern, Raviv Raich, Sarah Hadley, A. Hadley, Matthew Betts. Journal of the Acoustical Society of America, 2012

312 citations recorded by the source corpus.

Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H. J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning.

Subfields: Developmental Biology, Ecology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/5a60fa14194de1c0a8e32b6a4c35c22cfcb77e3c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Developmental Biology

In Ecology

In Signal Processing

Citations in the corpus

Detection and Classification of Acoustic Scenes and Events (2015, background): “Finally, a number of proposed systems focus on the detection and classification of specific sound events from environmental audio scenes such as speech [24], birdsong [25], musical instrument and other harmonic sounds [26], pornographic sounds [27] or hazardous events [28].”
Data-efficient weakly supervised learning for low-resource audio event detection using deep learning (2018, background): “In [5, 6, 7] the authors try to exploit weak labels in birdsong detection and bird species classification, while in [8] singing voice is pinpointed from weakly labelled examples.”
Improving distribution data of threatened species by combining acoustic monitoring and occupancy modelling (2016, methodology): “For example, automated species identification methods have been used to identify vocalizations of insects (Chesmore 2004), birds (Briggs et al. 2012), bats (Walters et al. 2012), primates (Kalan et al. 2015), whales (Murray, Mercado & Roitblat 1998) and amphibians (Ospina et al. 2013).”