Source Separation of Piano Concertos with Test-Time Adaptation

Music source separation (MSS) aims at decomposing a music recording into constituent sources, such as a lead instrument and the accompaniment. Despite the difficulties in MSS due to the high correlation of musical sources in time and frequency, deep neural networks (DNNs) have led to substantial improvements to accomplish this task. For training supervised machine learning models such as DNNs, isolated sources are required. In the case of popular music, one can exploit open-source datasets which involve multitrack recordings of vocals, bass, and drums. For western classical music, however, isolated sources are generally not available. In this article, we consider the case of piano concertos, which are composed for a pianist typically accompanied by an orchestra. The lack of multitrack recordings makes training supervised machine learning models for the separation of piano and orchestra challenging. To overcome this problem, we generate artificial training material by randomly mixing sections of the solo piano repertoire (e.g., piano sonatas) and orchestral pieces without piano (e.g., symphonies) to train state-of-the-art DNN models for MSS. As our main contribution, we propose a test-time adaptation (TTA) procedure, which exploits random mixtures of the piano-only and orchestra-only parts in the test data to further improve the separation quality