Content-based retrieval for music collections

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

68 Citations (Scopus)

Abstract

A content-based retrieval model for tackling the mismatch problems specific to music data is proposed and implemented. The system uses a pitch profile encoding for queries in any key and an n-note indexing method for approximate matching in sub-linear time. A distinct function that extracts key melodies for query suggestion is developed. The Web-based system provides flexible user interface for query formulation and result browsing. Users can search the system by a short sequence of notes, by uploading a file created by singing, or by clicking suggested key melodies without input. Experiments show that the pitch profile encoding and a 3-note indexing are able to overcome the key mismatch problem and the random errors caused by pitch error, note deletion and insertion. The use of extracted key melodies improves performance over direct search of the music database. For the type of burst mismatch, a query expansion approach is applied.

Original languageEnglish
Title of host publicationProceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999
PublisherAssociation for Computing Machinery, Inc
Pages176-182
Number of pages7
ISBN (Electronic)1581130961, 9781581130966
DOIs
Publication statusPublished - 1999 Aug 1
Event22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999 - Berkeley, United States
Duration: 1999 Aug 151999 Aug 19

Publication series

NameProceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999

Other

Other22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999
CountryUnited States
CityBerkeley
Period99/8/1599/8/19

Fingerprint

Content based retrieval
Random errors
User interfaces
Experiments

Keywords

  • Approximate string matching
  • Key melody extraction
  • Music indexing
  • Music retrieval
  • Pitch profile encoding
  • Query suggestion

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Information Systems

Cite this

Tseng, Y. H. (1999). Content-based retrieval for music collections. In Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999 (pp. 176-182). (Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999). Association for Computing Machinery, Inc. https://doi.org/10.1145/312624.312675

Content-based retrieval for music collections. / Tseng, Yuen Hsien.

Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999. Association for Computing Machinery, Inc, 1999. p. 176-182 (Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999).

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

Tseng, YH 1999, Content-based retrieval for music collections. in Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999. Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999, Association for Computing Machinery, Inc, pp. 176-182, 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999, Berkeley, United States, 99/8/15. https://doi.org/10.1145/312624.312675
Tseng YH. Content-based retrieval for music collections. In Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999. Association for Computing Machinery, Inc. 1999. p. 176-182. (Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999). https://doi.org/10.1145/312624.312675
Tseng, Yuen Hsien. / Content-based retrieval for music collections. Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999. Association for Computing Machinery, Inc, 1999. pp. 176-182 (Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999).
@inproceedings{a93d7f12962148fc872c9c2cdb455d01,
title = "Content-based retrieval for music collections",
abstract = "A content-based retrieval model for tackling the mismatch problems specific to music data is proposed and implemented. The system uses a pitch profile encoding for queries in any key and an n-note indexing method for approximate matching in sub-linear time. A distinct function that extracts key melodies for query suggestion is developed. The Web-based system provides flexible user interface for query formulation and result browsing. Users can search the system by a short sequence of notes, by uploading a file created by singing, or by clicking suggested key melodies without input. Experiments show that the pitch profile encoding and a 3-note indexing are able to overcome the key mismatch problem and the random errors caused by pitch error, note deletion and insertion. The use of extracted key melodies improves performance over direct search of the music database. For the type of burst mismatch, a query expansion approach is applied.",
keywords = "Approximate string matching, Key melody extraction, Music indexing, Music retrieval, Pitch profile encoding, Query suggestion",
author = "Tseng, {Yuen Hsien}",
year = "1999",
month = "8",
day = "1",
doi = "10.1145/312624.312675",
language = "English",
series = "Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999",
publisher = "Association for Computing Machinery, Inc",
pages = "176--182",
booktitle = "Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999",

}

TY - GEN

T1 - Content-based retrieval for music collections

AU - Tseng, Yuen Hsien

PY - 1999/8/1

Y1 - 1999/8/1

N2 - A content-based retrieval model for tackling the mismatch problems specific to music data is proposed and implemented. The system uses a pitch profile encoding for queries in any key and an n-note indexing method for approximate matching in sub-linear time. A distinct function that extracts key melodies for query suggestion is developed. The Web-based system provides flexible user interface for query formulation and result browsing. Users can search the system by a short sequence of notes, by uploading a file created by singing, or by clicking suggested key melodies without input. Experiments show that the pitch profile encoding and a 3-note indexing are able to overcome the key mismatch problem and the random errors caused by pitch error, note deletion and insertion. The use of extracted key melodies improves performance over direct search of the music database. For the type of burst mismatch, a query expansion approach is applied.

AB - A content-based retrieval model for tackling the mismatch problems specific to music data is proposed and implemented. The system uses a pitch profile encoding for queries in any key and an n-note indexing method for approximate matching in sub-linear time. A distinct function that extracts key melodies for query suggestion is developed. The Web-based system provides flexible user interface for query formulation and result browsing. Users can search the system by a short sequence of notes, by uploading a file created by singing, or by clicking suggested key melodies without input. Experiments show that the pitch profile encoding and a 3-note indexing are able to overcome the key mismatch problem and the random errors caused by pitch error, note deletion and insertion. The use of extracted key melodies improves performance over direct search of the music database. For the type of burst mismatch, a query expansion approach is applied.

KW - Approximate string matching

KW - Key melody extraction

KW - Music indexing

KW - Music retrieval

KW - Pitch profile encoding

KW - Query suggestion

UR - http://www.scopus.com/inward/record.url?scp=84889288359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889288359&partnerID=8YFLogxK

U2 - 10.1145/312624.312675

DO - 10.1145/312624.312675

M3 - Conference contribution

AN - SCOPUS:84889288359

T3 - Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999

SP - 176

EP - 182

BT - Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999

PB - Association for Computing Machinery, Inc

ER -