TY - GEN
T1 - Cover song identification with metric learning using distance as a feature
AU - Heo, Hoon
AU - Kim, Hyunwoo J.
AU - Kim, Wan Soo
AU - Lee, Kyogu
N1 - Funding Information:
This research project was supported by Ministry of Culture, Sports and Tourism (MCST) and from Korea Copyright Commission in 2017. [Development of predictive detection technology for the search for the related works and the prevention of copyright infringement]
Publisher Copyright:
© 2019 Hoon Heo, Hyunwoo J. Kim,Wan Soo Kim, Kyogu Lee.
PY - 2017
Y1 - 2017
N2 - Most of cover song identification algorithms are based on the pairwise (dis)similarity between two songs which are represented by harmonic features such as chroma, and therefore the choice of a distance measure and a feature has a significant impact on performance. Furthermore, since the similarity measure is query-dependent, it cannot represent an absolute distance measure. In this paper, we present a novel approach to tackle the cover song identification problem from a new perspective. We first construct a set of core songs, and represent each song in a high-dimensional space where each dimension indicates the pairwise distance between the given song and the other in the pre-defined core set. There are several advantages to this. First, using a number of reference songs in the core set, we make the most of relative distances to many other songs. Second, as all songs are transformed into the same high-dimensional space, kernel methods and metric learning are exploited for distance computation. Third, our approach does not depend on the computation method for the pairwise distance, and thus can use any existing algorithms. Experimental results confirm that the proposed approach achieved a large performance gain compared to the state-of-the-art methods.
AB - Most of cover song identification algorithms are based on the pairwise (dis)similarity between two songs which are represented by harmonic features such as chroma, and therefore the choice of a distance measure and a feature has a significant impact on performance. Furthermore, since the similarity measure is query-dependent, it cannot represent an absolute distance measure. In this paper, we present a novel approach to tackle the cover song identification problem from a new perspective. We first construct a set of core songs, and represent each song in a high-dimensional space where each dimension indicates the pairwise distance between the given song and the other in the pre-defined core set. There are several advantages to this. First, using a number of reference songs in the core set, we make the most of relative distances to many other songs. Second, as all songs are transformed into the same high-dimensional space, kernel methods and metric learning are exploited for distance computation. Third, our approach does not depend on the computation method for the pairwise distance, and thus can use any existing algorithms. Experimental results confirm that the proposed approach achieved a large performance gain compared to the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85054236711&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85054236711
T3 - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
SP - 628
EP - 634
BT - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
A2 - Cunningham, Sally Jo
A2 - Duan, Zhiyao
A2 - Hu, Xiao
A2 - Turnbull, Douglas
PB - International Society for Music Information Retrieval
T2 - 18th International Society for Music Information Retrieval Conference, ISMIR 2017
Y2 - 23 October 2017 through 27 October 2017
ER -