Rhythm Inference From Audio Recordings of Irish Traditional Music

Pierre Beauguitte

doi:10.21427/d74b2n

Rhythm Inference From Audio Recordings of Irish Traditional Music

Pierre Beauguitte

Technological University Dublin

Research output: Contribution to conference › Paper › peer-review

Abstract

A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collec- ion of session recordings, and high accuracy scores are reported. A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collection of session recordings, and high accuracy scores are reported.

Original language	English
DOIs	https://doi.org/10.21427/d74b2n
Publication status	Published - 2018
Event	8th International Workshop on Folk Music Analysis - Thessaloniki, Greece Duration: 26 Jun 2018 → 29 Jun 2018

Conference

Conference	8th International Workshop on Folk Music Analysis
Country/Territory	Greece
City	Thessaloniki
Period	26/06/18 → 29/06/18

Keywords

rhythmic information
audio recordings
Irish traditional tunes
repetitive nature
spectral features
autocorrelation
logistic regression models
session recordings
accuracy scores

Access to Document

10.21427/d74b2nLicence: CC BY-NC-SA

Cite this

@conference{82236176e9bd4963abc15815e69f3b9d,

title = "Rhythm Inference From Audio Recordings of Irish Traditional Music",

abstract = "A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collec- ion of session recordings, and high accuracy scores are reported. A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collection of session recordings, and high accuracy scores are reported.",

keywords = "rhythmic information, audio recordings, Irish traditional tunes, repetitive nature, spectral features, autocorrelation, logistic regression models, session recordings, accuracy scores",

author = "Pierre Beauguitte",

year = "2018",

doi = "10.21427/d74b2n",

language = "English",

note = "8th International Workshop on Folk Music Analysis ; Conference date: 26-06-2018 Through 29-06-2018",

}

TY - CONF

T1 - Rhythm Inference From Audio Recordings of Irish Traditional Music

AU - Beauguitte, Pierre

PY - 2018

Y1 - 2018

N2 - A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collec- ion of session recordings, and high accuracy scores are reported. A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collection of session recordings, and high accuracy scores are reported.

AB - A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collec- ion of session recordings, and high accuracy scores are reported. A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collection of session recordings, and high accuracy scores are reported.

KW - rhythmic information

KW - audio recordings

KW - Irish traditional tunes

KW - repetitive nature

KW - spectral features

KW - autocorrelation

KW - logistic regression models

KW - session recordings

KW - accuracy scores

U2 - 10.21427/d74b2n

DO - 10.21427/d74b2n

M3 - Paper

T2 - 8th International Workshop on Folk Music Analysis

Y2 - 26 June 2018 through 29 June 2018

ER -

Rhythm Inference From Audio Recordings of Irish Traditional Music

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this