DocumentCode :
3518351
Title :
Learning a music similarity measure on automatic annotations with application to playlist generation
Author :
Xiao, Linxing ; Lu, Lie ; Seide, Frank ; Zhou, Jie
Author_Institution :
Microsoft Res. Asia, Beijing
fYear :
2009
fDate :
19-24 April 2009
Firstpage :
1885
Lastpage :
1888
Abstract :
This paper presents an approach to learn a better music similarity measure and presents an application to music playlist generation. Different from previous work, in our approach, automatically detected music attributes are used to represent each song. A set of kernels is employed in similarity measure, with each kernel measuring on a subset of music attributes and having a different importance weight. In automatic music playlist generation, a ranking method is presented, which considers multiple seed songs and possible outlier seed. Experiments show the effectiveness of the proposed approach, and the quality of the playlist generated based on automatic annotations is comparable to that based on manual annotations.
Keywords :
information retrieval; music; automatic annotation; music playlist generation; music similarity measure; ranking method; Asia; Automation; Humans; Information science; Intelligent systems; Kernel; Laboratories; Multiple signal classification; Music information retrieval; Recommender systems; Music similarity; music annotation; music recommendation; playlist generation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
ISSN :
1520-6149
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2009.4959976
Filename :
4959976
Link To Document :
بازگشت