Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Randall Balestriero is active.

Publication


Featured researches published by Randall Balestriero.


Journal of the Acoustical Society of America | 2015

Enhanced feature extraction using the Morlet transform on 1 MHz recordings reveals the complex nature of Amazon River dolphin (Inia geoffrensis) clicks

Marie Trone; Hervé Glotin; Randall Balestriero; David E. Bonnett

The Amazon River dolphin lives exclusively in freshwater throughout the Amazon River watershed, a dynamic and acoustically complex habitat. Although generally considered a relatively non-vocal species, recent evidence suggests that these animals are acoustically active, producing tremendous quantities of high-frequency, pulsed signals. Moreover, these pulsed signals appear to be considerably more complex than previously believed. This study explored the high-frequency pulsed emanations produced by Amazon River dolphins in Peru. Audio recordings were made using a two hydrophone array, one of which was sampled at 1 MHz, in August of 2015. Digitized recordings were analyzed using FFT and Morlet wavelets. Subsequently, unsupervised machine learning attempted to delineate various click categories based upon inter-click intervals, the frequency bandwidth of each click, and the formants contained within each click. Although the Morlet transform is much more robust and accurate for higher frequencies than the FFT...


168th Meeting of the Acoustical Society of America | 2015

Heterogeneity of Amazon River dolphin high-frequency clicks: Current Odontoceti bioacoustic terminology in need of standardization

Marie Trone; Hervé Glotin; Randall Balestriero; David E. Bonnett; Jerry Blakefield

The quality and quantity of acoustical data available to researchers are rapidly increasing with advances in technology. Recording cetaceans with a 500 kHz sampling rate provides a more complete signal representation than traditional sampling at 96 kHz and lower. Such sampling provides a profusion of data concerning various parameters, such as click duration, inter-click intervals, frequency, amplitude and phase. However, there is disagreement in the literature in the use and definitions of these acoustic terms and parameters. In this study, Amazon River dolphins (Inia geoffrensis) were recorded using a 500 kHz sampling rate in the Peruvian Amazon River watershed. Subsequent spectral analyses, including time waveforms, fast Fourier transforms and wavelet scalograms, demonstrate acoustic signals with differing characteristics. These high-frequency, broadband signals are compared, and differences are highlighted, despite the fact that currently an unambiguous way to describe these acoustic signals is lackin...


Journal of the Acoustical Society of America | 2014

All clicks are not created equally: Variations in high-frequency acoustic signal parameters of the Amazon river dolphin (Inia geoffrensis)

Marie Trone; Randall Balestriero; Hervé Glotin; Bonnett E. David

The quality and quantity of acoustical data available to researchers are rapidly increasing with advances in technology. Recording cetaceans with a 500 kHz sampling rate provides a more complete signal representation than traditional sampling at 96 kHz and lower. Such sampling provides a profusion of data concerning various parameters, such as click duration, inter-click intervals, frequency, amplitude, and phase. However, there is disagreement in the literature in the use and definitions of these acoustic terms and parameters. In this study, Amazon River dolphins (Inia geoffrensis) were recorded using a 500 kHz sampling rate in the Peruvian Amazon River watershed. Subsequent spectral analyses, including time waveforms, fast Fourier transforms and wavelet scalograms, demonstrate acoustic signals with differing characteristics. These high frequency, broadband signals are compared, and differences are highlighted, despite the fact that currently an unambiguous way to describe these acoustic signals is lacki...


international conference on machine learning | 2018

A Spline Theory of Deep Networks.

Randall Balestriero; Richard G. Baraniuk


international conference on machine learning | 2018

A Spline Theory of Deep Learning

Randall Balestriero; Richard G. Baraniuk


arXiv: Machine Learning | 2018

A Spline Theory of Deep Networks (Extended Version).

Randall Balestriero; Richard G. Baraniuk


arXiv: Machine Learning | 2017

Linear Time Complexity Deep Fourier Scattering Network and Extension to Nonlinear Invariants

Randall Balestriero; Hervé Glotin


arXiv: Sound | 2016

Fast Chirplet Transform feeding CNN, application to orca and bird bioacoustics.

Hervé Glotin; Julien Ricard; Randall Balestriero


international conference on machine learning | 2018

Spline Filters For End-to-End Deep Learning

Randall Balestriero; Romain Cosentino; Hervé Glotin; Ankit B. Patel; Richard G. Baraniuk


arXiv: Machine Learning | 2018

Mad Max: Affine Spline Insights into Deep Learning

Randall Balestriero; Richard G. Baraniuk

Collaboration


Dive into the Randall Balestriero's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar

Hervé Glotin

Aix-Marseille University

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Vincent Roger

Centre national de la recherche scientifique

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Maxence Ferrari

Centre national de la recherche scientifique

View shared research outputs
Top Co-Authors

Avatar

Pascale Giraudet

Centre national de la recherche scientifique

View shared research outputs
Top Co-Authors

Avatar

Jared Towers

Fisheries and Oceans Canada

View shared research outputs
Researchain Logo
Decentralizing Knowledge