Cover Song Synthesis by Analogy

TL;DR

This paper introduces a novel method for synthesizing cover songs in the style of a different artist by leveraging cover song analogies, beat synchronization, joint NMF, and audio mosaicing to achieve style transfer.

Contribution

The work presents a new approach to cover song synthesis using analogy-based constraints, beat alignment, joint NMF, and audio mosaicing, enabling style transfer between cover versions.

Findings

Successfully synthesized cover versions in various examples.

Demonstrated style transfer from one artist to another.

Showcased effectiveness on popular songs like 'Bad' by Michael Jackson.

Abstract

In this work, we pose and address the following "cover song analogies" problem: given a song A by artist 1 and a cover song A' of this song by artist 2, and given a different song B by artist 1, synthesize a song B' which is a cover of B in the style of artist 2. Normally, such a polyphonic style transfer problem would be quite challenging, but we show how the cover songs example constrains the problem, making it easier to solve. First, we extract the longest common beat-synchronous subsequence between A and A', and we time stretch the corresponding beat intervals in A' so that they align with A. We then derive a version of joint 2D convolutional NMF, which we apply to the constant-Q spectrograms of the synchronized segments to learn a translation dictionary of sound templates from A to A'. Finally, we apply the learned templates as filters to the song B, and we mash up the translated filtered components into the synthesized song B' using audio mosaicing. We showcase our algorithm on several examples, including a synthesized cover version of Michael Jackson's "Bad" by Alien Ant Farm, learned from the latter's "Smooth Criminal" cover.'