Automatic harmonic analysis has been an enduring focus of the MIR community, and has enjoyed a particularly vigorous revival of interest in the machine-learning age. We focus here on the specific case of Roman numeral analysis which, by virtue of requiring key/functional information in addition to chords, may be viewed as an acutely challenging use case. We report on three main developments. First, we provide a new meta-corpus bringing together all existing Roman numeral analysis datasets; this offers greater scale and diversity, not only of the music represented, but also of human analytical viewpoints. Second, we examine best practices in the encoding of pitch, time, and harmony for machine learning tasks. The main contribution here is the introduction of full pitch spelling to such a system, an absolute must for the comprehensive study of musical harmony. Third, we devised and tested several neural network architectures and compared their relative accuracy. In the best-performing of these models, convolutional layers gather the local information needed to analyse the chord at a given moment while a recurrent part learns longer-range harmonic progressions. Altogether, our best representation and architecture produce a small but significant improvement on overall accuracy while simultaneously integrating full pitch spelling. This enables the system to retain important information from the musical sources and provide more meaningful predictions for any new input.
This article is aimed at two groups of readers. First, we present an interactive guide to pitch on the pedal harp for anyone wishing to teach or learn about harp pedaling and its associated pitch possibilities. We originally created this in response to a pedagogical need for such a resource in the teaching of composition and orchestration.Secondly, for composers and theorists seeking a more comprehensive understanding of what can be done on this unique instrument, we present a range of empirical-theoretical observations about the properties and prevalence of pitch structures on the pedal harp and the routes among them. This is particularly relevant to those interested in extended-tonal and atonal repertoires. A concluding section discusses prospective theoretical developments and analytical applications.
This article explores recent, radical developments in the ways in which new music is programmed and presented. It is contextualised by a brief survey of new music programming across the history of public concert-giving, and by several new interviews with industry professionals in the UK. These illustrate various rationales behind current practice including the dissatisfaction with traditional modes of concert-giving where appropriate. They also inform the author's conviction that different branches of new music benefit from different forms of presentation, acknowledging the importance of innovative forms to certain new styles.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.