Calibration of a two-state pitch-wise HMM method for note segmentation in Automatic Music Transcription systems

TL;DR

This paper introduces a two-state Hidden Markov Model for note segmentation in automatic music transcription, demonstrating that HMM-based soft thresholding with optimized parameters improves transcription accuracy across various scenarios.

Contribution

The study presents a novel parametrization of the HMM sigmoid function and compares fixed thresholding with HMM-based soft thresholding for note segmentation.

Findings

HMM soft thresholding outperforms fixed thresholding in transcription accuracy.

Optimized parameters {alpha, beta} significantly enhance segmentation performance.

Evaluation follows MIREX standards using the MAPS dataset.

Abstract

Many methods for automatic music transcription involves a multi-pitch estimation method that estimates an activity score for each pitch. A second processing step, called note segmentation, has to be performed for each pitch in order to identify the time intervals when the notes are played. In this study, a pitch-wise two-state on/off firstorder Hidden Markov Model (HMM) is developed for note segmentation. A complete parametrization of the HMM sigmoid function is proposed, based on its original regression formulation, including a parameter alpha of slope smoothing and beta? of thresholding contrast. A comparative evaluation of different note segmentation strategies was performed, differentiated according to whether they use a fixed threshold, called "Hard Thresholding" (HT), or a HMM-based thresholding method, called "Soft Thresholding" (ST). This evaluation was done following MIREX standards and using the MAPS dataset. Also, different transcription scenarios and recording natures were tested using three units of the Degradation toolbox. Results show that note segmentation through a HMM soft thresholding with a data-based optimization of the {alpha,beta} parameter couple significantly enhances transcription performance.