Fuzzy analysis in pitch class determination for polyphonic audio key finding

Ching-Hua Chuan, Elaine Chew

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)

Abstract

This paper presents a fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information. Errors in audio key finding, typically incorrect assignments of closely related keys, commonly result from imprecise pitch class determination and biases introduced by the quality of the sound. Our technique is motivated by hypotheses on the sources of audio key finding errors, and uses fuzzy analysis to reduce the errors caused by noisy detection of lower pitches, and to refine the biased raw frequency data, in order to extract more correct pitch classes. We compare the proposed system to two others, an earlier one employing only peak detection from FFT results, and another providing direct key finding from MIDI. All three used the same key finding algorithm (Chew's Spiral Array CEG algorithm) and the same 410 classical music pieces (ranging from Baroque to Contemporary). Considering only the first 15 seconds of music in each piece, the proposed fuzzy analysis technique outperforms the peak detection method by 12.18% on average, matches the performance of direct key finding from MIDI 41.73% of the time, and achieves an overall maximum correct rate of 75.25% (compared to 80.34% for MIDI key finding).

Original languageEnglish (US)
Title of host publicationISMIR 2005 - 6th International Conference on Music Information Retrieval
Pages296-303
Number of pages8
StatePublished - Dec 1 2005
Externally publishedYes
Event6th International Conference on Music Information Retrieval, ISMIR 2005 - London, United Kingdom
Duration: Sep 11 2005Sep 15 2005

Other

Other6th International Conference on Music Information Retrieval, ISMIR 2005
CountryUnited Kingdom
CityLondon
Period9/11/059/15/05

Fingerprint

Fast Fourier transforms
Acoustic waves
Fuzzy
Polyphonic
Music
Baroque
Sound
Classical music
Related Keys
Spiral
Assignment

Keywords

  • Audio key finding
  • Fuzzy analysis
  • Key proximity
  • Pitch classes

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Chuan, C-H., & Chew, E. (2005). Fuzzy analysis in pitch class determination for polyphonic audio key finding. In ISMIR 2005 - 6th International Conference on Music Information Retrieval (pp. 296-303)

Fuzzy analysis in pitch class determination for polyphonic audio key finding. / Chuan, Ching-Hua; Chew, Elaine.

ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. p. 296-303.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chuan, C-H & Chew, E 2005, Fuzzy analysis in pitch class determination for polyphonic audio key finding. in ISMIR 2005 - 6th International Conference on Music Information Retrieval. pp. 296-303, 6th International Conference on Music Information Retrieval, ISMIR 2005, London, United Kingdom, 9/11/05.
Chuan C-H, Chew E. Fuzzy analysis in pitch class determination for polyphonic audio key finding. In ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. p. 296-303
Chuan, Ching-Hua ; Chew, Elaine. / Fuzzy analysis in pitch class determination for polyphonic audio key finding. ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. pp. 296-303
@inproceedings{82d1e6d32b1a4a4abb45d43dcfbd05c3,
title = "Fuzzy analysis in pitch class determination for polyphonic audio key finding",
abstract = "This paper presents a fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information. Errors in audio key finding, typically incorrect assignments of closely related keys, commonly result from imprecise pitch class determination and biases introduced by the quality of the sound. Our technique is motivated by hypotheses on the sources of audio key finding errors, and uses fuzzy analysis to reduce the errors caused by noisy detection of lower pitches, and to refine the biased raw frequency data, in order to extract more correct pitch classes. We compare the proposed system to two others, an earlier one employing only peak detection from FFT results, and another providing direct key finding from MIDI. All three used the same key finding algorithm (Chew's Spiral Array CEG algorithm) and the same 410 classical music pieces (ranging from Baroque to Contemporary). Considering only the first 15 seconds of music in each piece, the proposed fuzzy analysis technique outperforms the peak detection method by 12.18{\%} on average, matches the performance of direct key finding from MIDI 41.73{\%} of the time, and achieves an overall maximum correct rate of 75.25{\%} (compared to 80.34{\%} for MIDI key finding).",
keywords = "Audio key finding, Fuzzy analysis, Key proximity, Pitch classes",
author = "Ching-Hua Chuan and Elaine Chew",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "9780955117909",
pages = "296--303",
booktitle = "ISMIR 2005 - 6th International Conference on Music Information Retrieval",

}

TY - GEN

T1 - Fuzzy analysis in pitch class determination for polyphonic audio key finding

AU - Chuan, Ching-Hua

AU - Chew, Elaine

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper presents a fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information. Errors in audio key finding, typically incorrect assignments of closely related keys, commonly result from imprecise pitch class determination and biases introduced by the quality of the sound. Our technique is motivated by hypotheses on the sources of audio key finding errors, and uses fuzzy analysis to reduce the errors caused by noisy detection of lower pitches, and to refine the biased raw frequency data, in order to extract more correct pitch classes. We compare the proposed system to two others, an earlier one employing only peak detection from FFT results, and another providing direct key finding from MIDI. All three used the same key finding algorithm (Chew's Spiral Array CEG algorithm) and the same 410 classical music pieces (ranging from Baroque to Contemporary). Considering only the first 15 seconds of music in each piece, the proposed fuzzy analysis technique outperforms the peak detection method by 12.18% on average, matches the performance of direct key finding from MIDI 41.73% of the time, and achieves an overall maximum correct rate of 75.25% (compared to 80.34% for MIDI key finding).

AB - This paper presents a fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information. Errors in audio key finding, typically incorrect assignments of closely related keys, commonly result from imprecise pitch class determination and biases introduced by the quality of the sound. Our technique is motivated by hypotheses on the sources of audio key finding errors, and uses fuzzy analysis to reduce the errors caused by noisy detection of lower pitches, and to refine the biased raw frequency data, in order to extract more correct pitch classes. We compare the proposed system to two others, an earlier one employing only peak detection from FFT results, and another providing direct key finding from MIDI. All three used the same key finding algorithm (Chew's Spiral Array CEG algorithm) and the same 410 classical music pieces (ranging from Baroque to Contemporary). Considering only the first 15 seconds of music in each piece, the proposed fuzzy analysis technique outperforms the peak detection method by 12.18% on average, matches the performance of direct key finding from MIDI 41.73% of the time, and achieves an overall maximum correct rate of 75.25% (compared to 80.34% for MIDI key finding).

KW - Audio key finding

KW - Fuzzy analysis

KW - Key proximity

KW - Pitch classes

UR - http://www.scopus.com/inward/record.url?scp=84873473031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873473031&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84873473031

SN - 9780955117909

SP - 296

EP - 303

BT - ISMIR 2005 - 6th International Conference on Music Information Retrieval

ER -