Trajectory Variance: AnUnsupervised Measure of Developmental Vocal Plasticity in Birdsong
2026-07-03 • Sound
Sound
AI summaryⓘ
The authors created a way to measure how much a bird's sound changes as it grows, without needing to label the types of sounds. Their method predicts how each vocalization would shift if the bird made it at different ages, capturing how flexible or 'plastic' the sound is. When tested on zebra finches, this measure helped tell apart learned songs from natural calls better than other methods. They also found that more flexible sounds tend to be more tonal and structured.
vocalizationtrajectory varianceplasticityautoencoderlatent spacezebra finchspectral flatnessdevelopmental stagessong syllablesinnate calls
Authors
Kanghwi Lee
Abstract
How much does a vocalization change over the course of development? We propose trajectory variance, a per-vocalization plasticity score that answers this question without type labels. A displacement model learns to predict age-conditioned shifts in autoencoder latent space; the variance of its predictions across target ages quantifies how much each vocalization would change if produced at different developmental stages. Evaluated on three zebra finches (183K-274K vocalizations, 40-101 days post-hatch), trajectory variance separates learned song syllables from innate calls (Cohen's d = 0.29-0.57, AUC = 0.58-0.67, after controlling for duration), while no nonparametric baseline achieves consistent separation. Trajectory variance also correlates with spectral flatness across all three birds (r = -0.48 to -0.75): more plastic vocalizations tend to have more tonal, structured spectra.