Abstract | ||
---|---|---|
Recently, advanced multimedia technologies enable a rapid growth of music data. It is accordingly a challenging issue to effectively retrieve the desired music pieces from a music collection. Traditional solutions for music retrieval can be divided into two types, namely text-based music retrieval and content-based music retrieval. However, it is difficult to satisfy both textual-percept and audio-content requirements from users. To tackle such problems, in this paper, we propose a new approach that retrieves music using fuzzy music-sense features and audio features. On one hand, the fuzzy music-sense features are adopted as auxiliary ones to increase the precision of content based music retrieval. On the other hand, the fuzzy music-sense features can also provide users with semantic music retrieval without precise query definitions. The experimental results reveal that, our proposed method can catch the relevant music accurately and semantically through effectively bridging music content to music sense. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/GRC.2014.6982846 | GrC |
Keywords | Field | DocType |
audio features,music data,textual-percept,query definitions,semantic networks,multimedia technologies,music,text-based music retrieval,content-based,fuzzy,music sense,music retrieval,semantic content-based music retrieval,fuzzy music sense features,text-based,music collection,audio-content requirements,content-based retrieval | Computer science,Fuzzy logic,Speech recognition | Conference |
Citations | PageRank | References |
1 | 0.37 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ja-Hwung Su | 1 | 329 | 24.53 |
Chun-Yen Wang | 2 | 1 | 0.37 |
Ting-Wei Chiu | 3 | 2 | 0.75 |
Josh Jia-Ching Ying | 4 | 327 | 13.47 |
Vincent S. Tseng | 5 | 2923 | 161.33 |