A similar music retrieval scheme based on musical mood variation

Sanghoon Jun, Byeong Jun Han, Een Jun Hwang

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

4 Citations (Scopus)

Abstract

Music evokes various human emotions or creates music moods through low level musical features. In fact, typical music consists of one or more moods and this can be used as an important factor for determining the similarity between music. In this paper, we propose a new music retrieval scheme based on the mood change pattern. For this, we first divide music clips into segments based on low level musical features. Then, we apply K-means clustering algorithm for grouping them into clusters with similar features. By assigning a unique mood symbol for each group, each music clip can be represented into a sequence of mood symbols. Then, we estimate the similarity of music based on the similarity of their musical mood sequence using the Longest Common Subsequence (LCS) algorithm. To evaluate the performance of our scheme, we carried out various experiments and measured the user evaluation. We report some of the results.

Original languageEnglish
Title of host publicationProceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009
Pages167-172
Number of pages6
DOIs
Publication statusPublished - 2009 Nov 12
Event2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009 - Dong Hoi, Viet Nam
Duration: 2009 Apr 12009 Apr 3

Other

Other2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009
CountryViet Nam
CityDong Hoi
Period09/4/109/4/3

Fingerprint

Clustering algorithms
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Software

Cite this

Jun, S., Han, B. J., & Hwang, E. J. (2009). A similar music retrieval scheme based on musical mood variation. In Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009 (pp. 167-172). [5175987] https://doi.org/10.1109/ACIIDS.2009.65

A similar music retrieval scheme based on musical mood variation. / Jun, Sanghoon; Han, Byeong Jun; Hwang, Een Jun.

Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009. 2009. p. 167-172 5175987.

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

Jun, S, Han, BJ & Hwang, EJ 2009, A similar music retrieval scheme based on musical mood variation. in Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009., 5175987, pp. 167-172, 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009, Dong Hoi, Viet Nam, 09/4/1. https://doi.org/10.1109/ACIIDS.2009.65
Jun S, Han BJ, Hwang EJ. A similar music retrieval scheme based on musical mood variation. In Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009. 2009. p. 167-172. 5175987 https://doi.org/10.1109/ACIIDS.2009.65
Jun, Sanghoon ; Han, Byeong Jun ; Hwang, Een Jun. / A similar music retrieval scheme based on musical mood variation. Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009. 2009. pp. 167-172
@inproceedings{d1a6b11f896e4a008d669f567c317853,
title = "A similar music retrieval scheme based on musical mood variation",
abstract = "Music evokes various human emotions or creates music moods through low level musical features. In fact, typical music consists of one or more moods and this can be used as an important factor for determining the similarity between music. In this paper, we propose a new music retrieval scheme based on the mood change pattern. For this, we first divide music clips into segments based on low level musical features. Then, we apply K-means clustering algorithm for grouping them into clusters with similar features. By assigning a unique mood symbol for each group, each music clip can be represented into a sequence of mood symbols. Then, we estimate the similarity of music based on the similarity of their musical mood sequence using the Longest Common Subsequence (LCS) algorithm. To evaluate the performance of our scheme, we carried out various experiments and measured the user evaluation. We report some of the results.",
author = "Sanghoon Jun and Han, {Byeong Jun} and Hwang, {Een Jun}",
year = "2009",
month = "11",
day = "12",
doi = "10.1109/ACIIDS.2009.65",
language = "English",
isbn = "9780769535807",
pages = "167--172",
booktitle = "Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009",

}

TY - GEN

T1 - A similar music retrieval scheme based on musical mood variation

AU - Jun, Sanghoon

AU - Han, Byeong Jun

AU - Hwang, Een Jun

PY - 2009/11/12

Y1 - 2009/11/12

N2 - Music evokes various human emotions or creates music moods through low level musical features. In fact, typical music consists of one or more moods and this can be used as an important factor for determining the similarity between music. In this paper, we propose a new music retrieval scheme based on the mood change pattern. For this, we first divide music clips into segments based on low level musical features. Then, we apply K-means clustering algorithm for grouping them into clusters with similar features. By assigning a unique mood symbol for each group, each music clip can be represented into a sequence of mood symbols. Then, we estimate the similarity of music based on the similarity of their musical mood sequence using the Longest Common Subsequence (LCS) algorithm. To evaluate the performance of our scheme, we carried out various experiments and measured the user evaluation. We report some of the results.

AB - Music evokes various human emotions or creates music moods through low level musical features. In fact, typical music consists of one or more moods and this can be used as an important factor for determining the similarity between music. In this paper, we propose a new music retrieval scheme based on the mood change pattern. For this, we first divide music clips into segments based on low level musical features. Then, we apply K-means clustering algorithm for grouping them into clusters with similar features. By assigning a unique mood symbol for each group, each music clip can be represented into a sequence of mood symbols. Then, we estimate the similarity of music based on the similarity of their musical mood sequence using the Longest Common Subsequence (LCS) algorithm. To evaluate the performance of our scheme, we carried out various experiments and measured the user evaluation. We report some of the results.

UR - http://www.scopus.com/inward/record.url?scp=70449119258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449119258&partnerID=8YFLogxK

U2 - 10.1109/ACIIDS.2009.65

DO - 10.1109/ACIIDS.2009.65

M3 - Conference contribution

SN - 9780769535807

SP - 167

EP - 172

BT - Proceedings - 2009 1st Asian Conference on Intelligent Information and Database Systems, ACIIDS 2009

ER -