Audio-to-Score Alignment using Transposition-invariant Features
This addresses the problem of aligning music scores to audio performances for researchers and practitioners in music analysis, offering a more flexible alternative to existing methods.
The paper tackled audio-to-score alignment for classical music by applying novel transposition-invariant audio features, which enabled accurate alignments between transposed scores and performances and outperformed widely used features on untransposed data.
Audio-to-score alignment is an important pre-processing step for in-depth analysis of classical music. In this paper, we apply novel transposition-invariant audio features to this task. These low-dimensional features represent local pitch intervals and are learned in an unsupervised fashion by a gated autoencoder. Our results show that the proposed features are indeed fully transposition-invariant and enable accurate alignments between transposed scores and performances. Furthermore, they can even outperform widely used features for audio-to-score alignment on `untransposed data', and thus are a viable and more flexible alternative to well-established features for music alignment and matching.