A supervised classification approach for note tracking in polyphonic piano transcription

Abstract

In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected notelevel abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano dataset report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than +10 % in terms of F-measure when compared to the baseline considered for both frame-level and notelevel evaluation.

A Comprehensive Review on Automatic Music Transcription: Survey of Transcription Techniques

“…In the end, better recall and precision were attained by the adopted model when compared to existing models. In 2018, Jose et al [60] introduced a machine learning based approach, which aimed at inferring note tracking automatically for piano music. Here, every pitch band was segmented into unique instances that were classified as non-active or active note events.…”

“…HMM system was adopted in [7] [60] and Otsu thresholding method was used in [9]. Markov random is used in [24].…”