Identifying polyphonic patterns from audio recordings using music segmentation techniques

Oriol Nieto, Morwaread Farbood

Research output: Contribution to conferencePaper

Abstract

This paper presents a method for discovering patterns of note collections that repeatedly occur in a piece of music. We assume occurrences of these patterns must appear at least twice across a musical work and that they may contain slight differences in harmony, timbre, or rhythm. We describe an algorithm that makes use of techniques from the music information retrieval task of music segmentation, which exploits repetitive features in order to automatically identify polyphonic musical patterns from audio recordings. The novel algorithm is assessed using the recently published JKU Patterns Development Dataset, and we show how it obtains state-of-the-art results employing the standard evaluation metrics.

Original languageEnglish (US)
Pages41-416
Number of pages376
StatePublished - Jan 1 2014
Event15th International Society for Music Information Retrieval Conference, ISMIR 2014 - Taipei, Taiwan, Province of China
Duration: Oct 27 2014Oct 31 2014

Conference

Conference15th International Society for Music Information Retrieval Conference, ISMIR 2014
CountryTaiwan, Province of China
CityTaipei
Period10/27/1410/31/14

Fingerprint

Audio recordings
Information retrieval
Audio Recordings
Segmentation
Music
Polyphonic

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Nieto, O., & Farbood, M. (2014). Identifying polyphonic patterns from audio recordings using music segmentation techniques. 41-416. Paper presented at 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, Province of China.

Identifying polyphonic patterns from audio recordings using music segmentation techniques. / Nieto, Oriol; Farbood, Morwaread.

2014. 41-416 Paper presented at 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, Province of China.

Research output: Contribution to conferencePaper

Nieto, O & Farbood, M 2014, 'Identifying polyphonic patterns from audio recordings using music segmentation techniques', Paper presented at 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, Province of China, 10/27/14 - 10/31/14 pp. 41-416.
Nieto O, Farbood M. Identifying polyphonic patterns from audio recordings using music segmentation techniques. 2014. Paper presented at 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, Province of China.
Nieto, Oriol ; Farbood, Morwaread. / Identifying polyphonic patterns from audio recordings using music segmentation techniques. Paper presented at 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, Province of China.376 p.
@conference{b032e288b23840329720c66c518ccd18,
title = "Identifying polyphonic patterns from audio recordings using music segmentation techniques",
abstract = "This paper presents a method for discovering patterns of note collections that repeatedly occur in a piece of music. We assume occurrences of these patterns must appear at least twice across a musical work and that they may contain slight differences in harmony, timbre, or rhythm. We describe an algorithm that makes use of techniques from the music information retrieval task of music segmentation, which exploits repetitive features in order to automatically identify polyphonic musical patterns from audio recordings. The novel algorithm is assessed using the recently published JKU Patterns Development Dataset, and we show how it obtains state-of-the-art results employing the standard evaluation metrics.",
author = "Oriol Nieto and Morwaread Farbood",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
pages = "41--416",
note = "15th International Society for Music Information Retrieval Conference, ISMIR 2014 ; Conference date: 27-10-2014 Through 31-10-2014",

}

TY - CONF

T1 - Identifying polyphonic patterns from audio recordings using music segmentation techniques

AU - Nieto, Oriol

AU - Farbood, Morwaread

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents a method for discovering patterns of note collections that repeatedly occur in a piece of music. We assume occurrences of these patterns must appear at least twice across a musical work and that they may contain slight differences in harmony, timbre, or rhythm. We describe an algorithm that makes use of techniques from the music information retrieval task of music segmentation, which exploits repetitive features in order to automatically identify polyphonic musical patterns from audio recordings. The novel algorithm is assessed using the recently published JKU Patterns Development Dataset, and we show how it obtains state-of-the-art results employing the standard evaluation metrics.

AB - This paper presents a method for discovering patterns of note collections that repeatedly occur in a piece of music. We assume occurrences of these patterns must appear at least twice across a musical work and that they may contain slight differences in harmony, timbre, or rhythm. We describe an algorithm that makes use of techniques from the music information retrieval task of music segmentation, which exploits repetitive features in order to automatically identify polyphonic musical patterns from audio recordings. The novel algorithm is assessed using the recently published JKU Patterns Development Dataset, and we show how it obtains state-of-the-art results employing the standard evaluation metrics.

UR - http://www.scopus.com/inward/record.url?scp=84946037794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946037794&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84946037794

SP - 41

EP - 416

ER -