Details
Original language | English |
---|---|
Title of host publication | Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09 |
Publisher | Association for Computing Machinery (ACM) |
Pages | 84-93 |
Number of pages | 10 |
ISBN (print) | 9781605583907 |
Publication status | Published - 9 Feb 2009 |
Event | 2nd ACM International Conference on Web Search and Data Mining, WSDM'09 - Barcelona, Spain Duration: 9 Feb 2009 → 12 Feb 2009 |
Publication series
Name | Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09 |
---|
Abstract
As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.
Keywords
- Exploiting tag semantics, Music genre classification, Relaxation labelling
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09. Association for Computing Machinery (ACM), 2009. p. 84-93 (Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Improving music genre classification using collaborative tagging data
AU - Chen, Ling
AU - Wright, Phillip
AU - Nejdl, Wolfgang
PY - 2009/2/9
Y1 - 2009/2/9
N2 - As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.
AB - As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.
KW - Exploiting tag semantics
KW - Music genre classification
KW - Relaxation labelling
UR - http://www.scopus.com/inward/record.url?scp=70349129938&partnerID=8YFLogxK
U2 - 10.1145/1498759.1498812
DO - 10.1145/1498759.1498812
M3 - Conference contribution
AN - SCOPUS:70349129938
SN - 9781605583907
T3 - Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09
SP - 84
EP - 93
BT - Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09
PB - Association for Computing Machinery (ACM)
T2 - 2nd ACM International Conference on Web Search and Data Mining, WSDM'09
Y2 - 9 February 2009 through 12 February 2009
ER -