Individual identity in songbirds: signal representations and metric learning for locating the information in complex corvid calls

TL;DR

This study applies advanced feature representations and metric learning to complex corvid calls, significantly improving individual identification accuracy and revealing key signal regions responsible for encoding identity.

Contribution

The paper introduces a novel combination of feature extraction and metric learning techniques to better understand and identify individual birds from complex calls.

Findings

Outperforms standard spectrogram-based methods in individual identification

Identifies specific time-frequency regions critical for recognition

Demonstrates the utility of computational methods in biological signal analysis

Abstract

Bird calls range from simple tones to rich dynamic multi-harmonic structures. The more complex calls are very poorly understood at present, such as those of the scientifically important corvid family (jackdaws, crows, ravens, etc.). Individual birds can recognise familiar individuals from calls, but where in the signal is this identity encoded? We studied the question by applying a combination of feature representations to a dataset of jackdaw calls, including linear predictive coding (LPC) and adaptive discrete Fourier transform (aDFT). We demonstrate through a classification paradigm that we can strongly outperform a standard spectrogram representation for identifying individuals, and we apply metric learning to determine which time-frequency regions contribute most strongly to robust individual identification. Computational methods can help to direct our search for understanding of these complex biological signals.