Estimating fundamental frequencies in polyphonic music remains a notoriously difficult task in Music Information Retrieval. While other tasks, such as beat tracking and chord recognition have seen improvement with the application of deep learning models, little work has been done to apply deep learning methods to fundamental frequency related tasks including multi-f0 and melody tracking, primar...

In this preliminary study, we measured event-related potentials (ERPs) to melodic expectancy violations in a cross-cultural context. Subjects (n= 10) were college-age students born and raised in the United States. Subjects heard 30 short melodies based in the Western folk tradition and 30 from North Indian classical music. Each melody was presented in its original and deviation form, and subjec...

The concept of a prototypical melody has been proposed to characterize sets of similar musical segments in a composition. In musicology, the degree of importance associated with a prototypical melody is proportional to the number of musical segments similar to it. In this paper, a novel approach is developed to extract all the prototypical melodies in a musical work. Our approach considers each...

This paper examines and compares vocal performances. It also follows the path of poem to melody to singing, and their interrelations. Results are demonstrated in examples in which comparison is made between performances of the same melody by two or more artists in: “Au Cimetière” by Berlioz, “Der Tod und das Mädchen” by Schubert, the Aria “In Questa Reggia” (Turandot) by Puccini, and the ariett...

We present preliminary work on automatic human-readable melody characterization. In order to obtain such a characterization, we (1) extract a set of statistical descriptors from the tracks in a dataset of MIDI files, (2) apply a rule induction algorithm to obtain a set of (crisp) classification rules for melody track identification, and (3) automatically transform the crisp rules into fuzzy rul...

To achieve my goal, I developed a theory of musical features inspired by Ullman's Goldilocks theory for visual features. I implemented a computer program that analyzes instrumental (MIDI) versions of the songs to extract relevant parameters for my model. This program also identifies music pieces based on a melody contour of varying length and complexity. Finally I experimentally verified the hy...

The present research addressed whether auditory feedback associated with a learned action sequence can activate the action representation of that sequence. Nonpianist participants learned to perform two melodies at a piano keyboard repeatedly during a trial. The participants heard feedback either from the melody they were performing (normal feedback) or from the other learned melody (termed alt...

Music transcription is a highly complex task that is difficult for automated algorithms, and equally challenging to people, even those with many years of musical training. Furthermore, there is a shortage of high-quality datasets for training automated transcription algorithms. In this research, we explore a semi-automated, crowdsourced approach to generate music transcriptions, by first runnin...

Melodies provide an important conceptual summarization of polyphonic audio. The extraction of melodic content has practical applications ranging from content-based audio retrieval to the analysis of musical structure. In contrast to previous transcription systems based on a model of the harmonic (or periodic) structure of musical pitches, we present a classification-based system for performing ...