Abstract | ||
---|---|---|
This paper proposes a popular music representation strategy based on the song's emotion. First, a piece of popular music is decomposed into chorus and verse segments through the proposed chorus detection algorithm. Three descriptive features: intensity, frequency band and rhythm regularity are extracted from the structured segments for emotion detection. A hierarchical Adaboost classifier is employed to recognize the emotion of a piece of popular music. The general emotion of the music is classified according to Thayer's model into four emotions: happy, angry, depressed and relaxed. Experiments conducted on a 350-popular-music database show the average recall and precision of our proposed chorus detection are approximately 95 % and 84 %, respectively; and the average precision rate of emotion detection is 92 %. Additional tests are performed on songs with cover versions in different lyrics and languages, and the resultant precision rate is 90 %. The proposes approaches have been tested and proven by the professional online music company, KKBOX Inc. and show promising performance for effectively and efficiently identifying the emotions of a variety of popular music. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/s11042-013-1687-2 | Multimedia Tools and Applications |
Keywords | Field | DocType |
rhythm,popular music,emotion,adaboost,chorus,verse,mfccs,Popular music,Chorus,Verse,MFCCs,Rhythm,Emotion,Adaboost | AdaBoost,Computer science,Emotion recognition,Precision and recall,Speech recognition,Popular music,Emotion detection,Lyrics,Chorus,Rhythm | Journal |
Volume | Issue | ISSN |
73 | 3 | 1380-7501 |
Citations | PageRank | References |
1 | 0.36 | 30 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chia-Hung Yeh | 1 | 367 | 42.15 |
Wen-Yu Tseng | 2 | 33 | 5.67 |
Chia-Yen Chen | 3 | 63 | 14.80 |
Yu-Dun Lin | 4 | 1 | 0.69 |
Yi-Ren Tsai | 5 | 1 | 0.36 |
Hsuan-I Bi | 6 | 1 | 0.36 |
Yu-Ching Lin | 7 | 1 | 0.36 |
Ho-Yi Lin | 8 | 1 | 0.36 |