Pitch tracking of bird vocalizations and an automated process using YIN-bird

O’Reilly, Colm; Harte, Naomi

doi:10.1080/23312025.2017.1322025

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For music, we used the University of Rochester Multi-Modal Music Performance (URMP) dataset, which contained recorded audio of various instruments playing classical music along with corresponding MIDI and pitch tracks (151). For bioacoustics, we used the Synth Birds Database (SynthBirdsDB) which contained recorded audio from a variety of bird species, with either harmonic or pure tone vocalizations (152). This dataset was compiled to develop pitch-tracking for bird vocalizations, so we used a subset of the data for which accurate pitch tracks were provided.…”

Section: Variable Class Distributionmentioning

confidence: 99%

Listening with generative models

Cusimano

Hewitt

McDermott

2023

Preprint

View full text Add to dashboard Cite

Perception has long been envisioned to use an internal model of the world to infer the causes of sensory signals. However, tests of inferential accounts of perception have been limited by computational intractability, as inference requires searching through complex hypothesis spaces. Here we revisit the idea of perception as inference in a world model, using auditory scene analysis as a case study. We applied contemporary computational tools to enable Bayesian inference in a structured generative model of auditory scenes. Model inferences accounted for many classic illusions. Unlike most previous accounts of auditory illusions, our model can be evaluated on any sound, and exhibited human-like perceptual organization for real-world sound mixtures. The combination of stimulus-computability and interpretable structure enable 'rich falsification', revealing additional assumptions about sound generation needed to explain perception. The results show how a single generative theory can account for the perception of both classic illusions and everyday sensory signals.

show abstract

Section: Variable Class Distributionmentioning

confidence: 99%

Listening with generative models

Cusimano

Hewitt

McDermott

2023

Preprint

View full text Add to dashboard Cite

show abstract

Measuring vocal difference in bird population pairs

O’Reilly

Analuddin

Kelly

et al. 2018

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Over time, a bird population's acoustic and morphological features can diverge from the parent species. A quantitative measure of difference between two populations of species/subspecies is extremely useful to zoologists. Work in this paper takes a dialect difference system first developed for speech and refines it to automatically measure vocalisation difference between bird populations by extracting pitch contours. The pitch contours are transposed into pitch codes. A variety of codebook schemes are proposed to represent the contour structure, including a vector quantization approach. The measure, called Bird Vocalisation Difference, is applied to bird populations with calls that are considered very similar, very different, and between these two extremes. Initial results are very promising, with the behaviour of the metric consistent with accepted levels of similarity for the populations tested to date. The influence of data size on the measure is investigated by using reduced datasets. Results of species pair classification using Gaussian mixture models with Mel-frequency cepstral coefficients is also given as a baseline indicator of class confusability.

show abstract

Pitch tracking of bird vocalizations and an automated process using YIN-bird

Cited by 2 publications

References 41 publications

Listening with generative models

Listening with generative models

Measuring vocal difference in bird population pairs

Contact Info

Product

Resources

About