This report details the creation of a new dataset named the Gunnlod dataset (after the Norse giantess who guarded the mead of poetry) for use in research in the field of machine learning as applied to music creation, particularly multi-modal music in the MIDI format of symbolic music representation. The dataset is based on a subset of approximately four fifths of the Lakh MIDI dataset. Each of the selected files has been processed to create an array representation of the file intended for easy use with machine learning models, as well as a taggram - a matrix of values specifying the degree to which the music exhibits certain traits at different points in time. These traits include genres (such as ”rock”, ”pop” and ”country”), instrumentation (such as ”flute”, ”vocals” and ”guitar”) as well as other more general descriptors (such as ”catchy”, ”quiet” and ”weird”). The trait values are generated by a preexisting machine learning model, circumventing the need for intense human labour. The dataset is intended to enable future researchers to create tools to aid in h‘uman creative tasks, such as a virtual ”composer’s assistant” capable of offering suggestions for melodies or drum beats based on the user’s requests. The code used to create Gunnlod can be found at https://gits-15.sys.kth.se/joeli/midiPipe. The report also includes an ethical analysis of the dataset rooted in the seven guidelines for ethical AI outlined in the framework Ethics guidelines for trustworthy AI commissioned by the European Commission. It concludes that the creation of Gunnlod raises concerns regarding Privacy and data governance and Diversity, non-discrimination and fairness, which are to some degree alleviated by its Transparency, and suggests ways to perform future research in ethical ways. / Denna rapport beskriver skapandet av ett nytt dataset namngivet Gunnlod (efter den jättinna som vaktade skaldemjödet) för bruk inom forskning inom maskininlärning applicerat på musikskapande, med särskilt fokus på multiinstrumental musik på MIDI-format. Datsetet är baserat på cirka fyra femtedelar av Lakh MIDI-datasetet. Varje utvald fil har använts för att skapa en matrisrepresentation därav avsett för enkelt bruk i maskinlärningsmodeller, samt ett taggram - en matris av värden på hur mycket musiken visar på specifika drag vid specifika tidpunkter. Dessa drag inkluderar genrer (såsom ”rock”, ”pop” och ”country”), instrumentation (såsom ”flute”, ”vocals” och ”guitar”) samt mer generellt beskrivande ord (såsom ”catchy”, ”quiet” och ”weird”). Dessa värden genereras av en förexisterande maskininlärningsmodell, vilket kringgår behovet av intensivt mänskligt arbete. Detta dataset är avsett att möjliggöra framtida forskare att skapa verktyg som hjälper människors kreativa processer, såsom en virtuell ”kompositörsassistent” som kan förse förslag på melodier eller trumkomp utifrån en användares förfrågan. Koden som användes för att skapa datasetet går att finna på https://gits-15.sys.kth.se/ joeli/midiPipe. Rapporten innehåller också en etisk analys av datasetet rotad i de sju riktlinjer som ges i ramverket Ethics guidelines for trustworthy AI, skapat på uppdrag av Europeiska kommissionen. Analysen visar på farhågor med Gunnlods skapelse inom områdena Privacy and data governance och Diversity, non-discrimination and fairness, som till viss grad avhjälps av dess höga grad av Transparency, och förslag framläggs på hur framtida forskning ska genomföras på ett etiskt sätt.

While it is important for systems intended to enhance musical creativity to define and explore musical ideas conceived by individual users, many limit musical freedom by focusing on maintaining musical structure, thereby impeding the user's freedom to explore his or her individual style. This dissertation presents a comprehensive body of work that introduces a new musical representation that allows users to explore a space of musical rules that are created from their own melodies. This representation, called functional scaffolding for musical composition (FSMC), exploits a simple yet powerful property of multipart compositions: The pattern of notes and rhythms in different instrumental parts of the same song are functionally related. That is, in principle, one part can be expressed as a function of another. Music in FSMC is represented accordingly as a functional relationship between an existing human composition, or scaffold, and an additional generated voice. This relationship is encoded by a type of artificial neural network called a compositional pattern producing network (CPPN). A human user without any musical expertise can then explore how these additional generated voices should relate to the scaffold through an interactive evolutionary process akin to animal breeding. The utility of this insight is validated by two implementations of FSMC called NEAT Drummer and MaestroGenesis, that respectively help users tailor drum patterns and complete multipart arrangements from as little as a single original monophonic track. The five major contributions of this work address the overarching hypothesis in this dissertation that functional relationships alone, rather than specialized music theory, are sufficient for generating plausible additional voices. First, to validate FSMC and determine whether plausible generated voices result from the human-composed scaffold or intrinsic properties of the CPPN, drum patterns are created with NEAT Drummer to accompany several different polyphonic pieces. Extending the FSMC approach to generate pitched voices, the second contribution reinforces the importance of functional transformations through quality assessments that indicate that some partially FSMC-generated pieces are indistinguishable from those that are fully human. While the third contribution focuses on constructing and exploring a space of plausible voices with MaestroGenesis, the fourth presents results from a two-year study where students discuss their creative experience with the program. Finally, the fifth contribution is a plugin for MaestroGenesis called MaestroGenesis Voice (MG-V) that provides users a more natural way to incorporate MaestroGenesis in their creative endeavors by allowing scaffold creation through the human voice. Together, the chapters in this dissertation constitute a comprehensive approach to assisted music generation, enabling creativity without the need for musical expertise.

Computer-generated music composition programs have yet to produce creative, natural sounding music. To date, most approaches constrain the search space heuristically while ignoring the inherent structure of music over time. To address this problem, this thesis introduces NEAT Drummer, which evolves a special kind of artificial neural network (ANN) called compositional pattern producing networks (CPPNs) with the NeuroEvolution of Augmenting Topologies (NEAT) method for evolving increasingly complex structures. CPPNs in NEAT Drummer input existing human compositions and output an accompanying drum track. The existing musical parts form a scaffold i.e. support structure, for the drum pattern outputs, thereby exploiting the functional relationship of drums to musical parts (e.g. to lead guitar, bru:is, etc.) The results are convincing drum patterns that follow the contours of the original song, validating a new approach to computergenerated music composition.