We propose a framework for audio-to-score alignment on piano performance that employs automatic music transcription (AMT) using neural networks. Even though the AMT result may contain some errors, the note prediction output can be regarded as a learned feature representation that is directly comparable to MIDI note or chroma representation. To this end, we employ two recurrent neural networks that work as the AMT-based feature extractors to the alignment algorithm. One predicts the presence of 88 notes or 12 chroma in frame-level and the other detects note onsets in 12 chroma. We combine the two types of learned features for the audio-to-score alignment. For comparability, we apply dynamic time warping as an alignment algorithm without any additional post-processing. We evaluate the proposed framework on the MAPS dataset and compare it to previous work. The result shows that the alignment framework with the learned features significantly improves the accuracy, achieving less than 10 ms in mean onset error.
View on arXiv