# Audio-to-Score Alignment using Transposition-invariant Features

arXiv: https://arxiv.org/abs/1807.07278 · HTML: https://mlsanity.com/paper/1807.07278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 1 of 1)

- [Just Label the Repeats for In-The-Wild Audio-to-Score Alignment](https://mlsanity.com/paper/2411.07428/) (2024)

## Abstract (arXiv)

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.