Early MFCC And HPCP Fusion for Robust Cover Song Identification

TL;DR

This paper introduces an unsupervised fusion method combining MFCC and HPCP features for robust cover song identification, significantly improving accuracy and establishing a new benchmark dataset.

Contribution

The authors propose a novel unsupervised fusion algorithm that combines MFCC and HPCP features, leveraging structural information for enhanced cover song identification.

Findings

Achieved a state-of-the-art mean reciprocal rank of 0.87 on the Covers80 dataset.

Introduced the Covers 1000 benchmark dataset with 1000 songs and 395 cover groups.

Attained an MRR of 0.9 on the new dataset for the first correctly identified song.

Abstract

While most schemes for automatic cover song identification have focused on note-based features such as HPCP and chord profiles, a few recent papers surprisingly showed that local self-similarities of MFCC-based features also have classification power for this task. Since MFCC and HPCP capture complementary information, we design an unsupervised algorithm that combines normalized, beat-synchronous blocks of these features using cross-similarity fusion before attempting to locally align a pair of songs. As an added bonus, our scheme naturally incorporates structural information in each song to fill in alignment gaps where both feature sets fail. We show a striking jump in performance over MFCC and HPCP alone, achieving a state of the art mean reciprocal rank of 0.87 on the Covers80 dataset. We also introduce a new medium-sized hand designed benchmark dataset called "Covers 1000," which consists of 395 cliques of cover songs for a total of 1000 songs, and we show that our algorithm achieves an MRR of 0.9 on this dataset for the first correctly identified song in a clique. We provide the precomputed HPCP and MFCC features, as well as beat intervals, for all songs in the Covers 1000 dataset for use in further research.