Evaluation of Chord and Chroma Features and Dynamic Time Warping Scores on Cover Song Identification Task

Abstract

Part 3: Data Analysis and Information RetrievalInternational audienceCover song identification has been a popular task within music information retrieval in the 20th century. The task is to identify a different version or performance of a previously recorded song. Unlike audio search for an exact matching song, this task has not yet been popularized among users, due to an ambiguous definition of a cover song and the complexity of the problem. With a great variety of methods proposed on the benchmarking challenges, it is increasingly difficult to compare advantages and disadvantages of the features and algorithms. We provide a comparison of three levels of feature extraction (chroma features, chroma vector distances, chord distances) and show how each level affects the results. We further distinguish five scores for dynamic time warping method, to find the best performance in conjunction with the features. Results were evaluated on covers80 and SecondHandSongs datasets and compared to the state-of-the-art

Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval

“…Among the various subtopics in content-based MIR, automatic chord estimation has received a considerable and sustained attention since its inception (Fujishima, 1999). Not only it is a very interesting and challenging problem, but also it has many applications in high-level tasks such as cover song identification (Marsík et al, 2017), genre classification (Pereira and Silla, 2017) or automatic accompaniment (Ojima et al, 2017). Also, there is a high demand on chord-based representations by users in the music community, as illustrated by the popularity of websites such as Ultimate Guitar 1 .…”