| Paper: | AE-L1.2 | ||
| Session: | Audio Structure, Similarity and Segmentation | ||
| Time: | Tuesday, May 16, 10:50 - 11:10 | ||
| Presentation: | Lecture | ||
| Topic: | Audio and Electroacoustics: Applications to Music | ||
| Title: | THE IMPORTANCE OF SEQUENCES IN MUSICAL SIMILARITY | ||
| Authors: | Michael Casey, University of London, United Kingdom; Malcolm Slaney, Yahoo! Research, United States | ||
| Abstract: | This paper demonstrates the importance of temporal sequences for passage-level music information retrieval. A number of audio analysis problems are solved successfully by using models that throw away the temporal sequence data. This paper suggests that we do not have this luxury when we consider a more difficult problem: that is finding musically similar passages within a narrow range of musical styles or within a musical piece itself. Our results demonstrate a significant improvement in performance for audio similarity measures using temporal sequences of features, and we show that quantizing the features to string-based representations also performs well. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012