Annotated Bibliography for the Class Presentation
on Singer Similarity
Kim, Y. and B. Whitman. 2002. Singer identification in popular music recordings using voice coding features. In Proceedings of the 2002 International Symposium on Music Information Retrieval.
Available: The paper can be found in the ISMIR online 2002 proceedings. (Last accessed March 10, 2005)
This paper is not too hard to understand. What makes this one different from the other is its use of harmonicity in its system analysis. Assumption is made on pop music. The classification of vocal signals is performed by the GMM and SVM methods.
Liu, C. and C. Huang. 2002. A singer identification technique for content-based classification of mp3 music objects. In Proceedings of the 2002 Conference on Information and Knowledge Management. 438-45.
This system differs from the other that it uses only
MP3 files and the approach focuses on phoneme segmentation and classification
via weighted k-Nearest Neighbors.
Tsai, W., H. Wang, D. Rodgers, S. Cheng, and H. Yu. 2003. Blind clustering of popular music recording based on singer voice characteristics. In Proceedings of the 2003 International Symposium on Music Information Retrieval. 67-73.
This paper involves quiet a lot of math but the concept is not too hard to graspe. The clustering system operates in an unsupervized manner. It also uses only pop music for testing.