Ensemble-based cover song detection
This addresses the challenge of scalable cover song detection for the music information retrieval community, though it is incremental as it builds on existing binary comparison methods.
The paper tackles the problem of audio-based cover song detection by introducing an ensemble-based method that considers sets of tracks and their relationships, resulting in significant performance improvements, especially when many versions of a composition exist.
Audio-based cover song detection has received much attention in the MIR community in the recent years. To date, the most popular formulation of the problem has been to compare the audio signals of two tracks and to make a binary decision based on this information only. However, leveraging additional signals might be key if one wants to solve the problem at an industrial scale. In this paper, we introduce an ensemble-based method that approaches the problem from a many-to-many perspective. Instead of considering pairs of tracks in isolation, we consider larger sets of potential versions for a given composition, and create and exploit the graph of relationships between these tracks. We show that this can result in a significant improvement in performance, in particular when the number of existing versions of a given composition is large.