Identifying `Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking

By D. Ellis, Graham E. Poliner. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2007

414 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Content-Based Music Information Retrieval: Current Directions and Future Challenges (2008, methodology): “Beat-based segmentation has been found to improve performance in cover song identification [ 28 ]”
Semantic Annotation and Retrieval of Music and Sound Effects (2008, background): “(without derivatives), chroma features [30], and fluctuation pat-”
Beat Tracking by Dynamic Programming (2007, methodology): “We have used this algorithm successfully as the basis of the beat-synchronous chroma features which underly our cover song detection system [Ellis and Poliner, 2007] which had the best performance by a wide margin in the MIREX-06 Cover Song Detection evaluation.”
A Survey of Audio-Based Music Classification and Annotation (2011, methodology): “Pitch class features like pitch class profile (PCP) [97] and harmonic pitch class profile (HPCP) [98] have been developed and widely used in various tasks like melody analysis and transcription [93], [99], [100].”