Popular Music Production Research Articles

Evaluating Feature Selection Algorithms for Machine Learning-Based Musical Instrument Identification in Monophonic Recordings

Musical instrument identification (MII) research has been studied as a subfield of the Music Information Retrieval (MIR) field. Conventional MII models are developed based on hierarchical models representing musical instrument families. However, for MII models to be used in the field of music production, they should be developed based on the arrangement-based functions of instruments in musical styles rather than these hierarchical models. This study investigates how the performance of machine learning based classification algorithms for Guitar, Bass guitar and Drum classes changes with different feature selection algorithms, considering a popular music production scenario. To determine the effect of feature statistics on model performance, Minimum Redundancy Maximum Relevance (mRMR), Chi-sqaure (Chi2), ReliefF, Analysis of Variance (ANOVA) and Kruskal Wallis feature selection algorithms were used. In the end, the neural network algorithm with wide hyperparameters (WNN) achieved the best classification accuracy (91.4%) when using the first 20 statistics suggested by the mRMR and ReliefF feature selection algorithms.

The performance of machine aesthetics: acoustic reimagining of electronic music

AbstractThis article explores the emergence of musical performance practices whereby electronic music styles, along with the musical and sonic characteristics inherent in their electronic production, are emulated through live musical performance using acoustic instrumentation. The article draws on Brummett's (1999) concept of ‘machine aesthetics’ to explore the emergence of these practices, whereby musicians emulate sonic and musical attributes of music usually produced by machines, without the use of machines. Utilising semi-structured interviews and musical analysis of records by Abstract Orchestra and GoGo Penguin, the article attempts to contextualise these practices within their broader function in popular music production and performance.

(Plat)formatted Creativity: Creating Music in the Age of Streaming

What impact does music streaming have on the production and aesthetics of popular music? Based on 15 qualitative interviews with Norwegian music creators, this article explores how music production is executed and interpreted under the paradigm of platformization. Following the concept of ‘creativity constraints’ – a concept highlighting the restraining and enabling possibilities inherent in the complex sets of constraints surrounding creative agency – this article proposes an analysis centered around three different views emphasizing the opportunities, the limitations, and the negotiations that are put into play throughout the processes of platformized music production. The article finds that the music creators continuously negotiate between these three different (partly opposing, partly overlapping) views when producing music, of which an exchange between emphasizing the democratizing and creatively liberating potential of platformization, and criticizing the commercializing and creatively standardizing effect platformization (and the attention economy) pose on contemporary music culture, constitutes the analysis discursive point of gravity. In this way, the article highlights various dialectics and contradictions concerning the ways in which popular music production develops under the paradigm of platformization.

“Be the Signal”

Popular music pedagogy has for decades educated students in the foundational skills of music production. Yet the agency of professional practitioners illuminates that music producers also utilise tacit skills in communication and psychology to garnish musical works that target aesthetic intentions. These soft skills take time to develop in young people and so pedagogy in this field must target this at the beginning of a student’s higher education journey. Pedagogy in this field is complex and previous research efforts have highlighted the usefulness of integrated formal and practice-led collaborative educational approaches. This study develops this discourse further by investigating the utility of pedagogical video resources used in a flipped educational framework. The subsequent case study of the course MPP 1 found that students valued this approach and highlighted video length, accessibility and the educator’s embodiment of practitioner traits as integral to their learning more holistic approaches to popular music production.

Plasticine Music – or the intimate social life of cultural objects

ABSTRACTWhy do you value recorded popular music? How does popular music sticks to our lives through time? This article presents the concept of Plasticine Music to explore the way music becomes an assemblage through our individual embodied history with it. The concept intends to expand on recent developments on the value of recorded popular music outside capital and production systems. By following scholarship from Music Sociology and Feminist Materialism it invites to consider how pieces of music become part of our biographies through emotional forces, embodied actions and affects that transform the way we relate to music; the music change and we change with it. It focuses on the materiality of music with modifiable qualities, flexibility, resistance and non fixity, which lead to multiple new shapes. Plasticine music is a form of changeling traditional conceptions of meaning and cultural consumption, as well as considering the affective force of cultural objects.

Research in Computational Expressive Music Performance and Popular Music Production: A Potential Field of Application?

In music, the interpreter manipulates the performance parameters in order to offer a sonic rendition of the piece that is capable of conveying specific expressive intentions. Since the 1980s, there has been growing interest in expressive music performance (EMP) and its computational modeling. This research field has two fundamental objectives: understanding the phenomenon of human musical interpretation and the automatic generation of expressive performances. Rule-based, statistical, machine, and deep learning approaches have been proposed, most of them devoted to the classical repertoire, in particular to piano pieces. On the contrary, we introduce the role of expressive performance within popular music and the contemporary ecology of pop music production based on the use of digital audio workstations (DAWs) and virtual instruments. After an analysis of the tools related to expressiveness commonly available to modern producers, we propose a detailed survey of research into the computational EMP field, highlighting the potential and limits of what is present in the literature with respect to the context of popular music, which by its nature cannot be completely superimposed to the classical one. In the concluding discussion, we suggest possible lines of future research in the field of computational expressiveness applied to pop music.

Using word embedding models to capture changing media discourses: a study on the role of legitimacy, gender and genre in 24,000 music reviews, 1999–2021

Studies suggest that popular music genres are increasingly discussed by cultural intermediaries in ‘legitimate’ or ‘highbrow’ terms, rather than merely ‘lowbrow’ commercial entertainment. In addition, popular music discourse as produced by such intermediaries has historically been decidedly masculine—a trait which tends to increase on par with legitimation. However, seeing that women are gradually gaining symbolic and numerical representation in popular music production, this may have been changing over the last decade(s). In this article, we assess how popular music discourse within a key music media outlet (Pitchfork) changed between 1999 and 2021. We use word embedding models—a novel technique in computational social science—to assess legitimacy and gender in the discourses used in 23,992 reviews, and how this varies between genres. We find four notable patterns. First, reviews increasingly use a discourse that legitimates popular music, while, second, also increasingly using more feminine terms. This does not, third, occur simultaneously; however, discourse is either legitimate or feminine. Finally, these patterns also differ based on which popular music genres are discussed. The overall pattern is consistently found in pop, electronic and experimental, but not in historically masculine genres rap/hip-hop, metal and jazz which seem rather resistant to discursive change.

Popular Music, Deviance and Moral Panics in Nigeria: The Music of Naira Marley

This paper interrogates the issue of deviance and moral panics associated with popular music production in Nigeria. Relying on qualitative and netnographic data, the paper explores contested perspectives on the music of Naira Marley, which is generally laden with censured themes of vulgarity, substance abuse, and loose sexuality. Naira Marley’s music has generated much moral controversy in Nigeria owing mainly to media criticisms, which follow from the bizarre subcultural lifestyles of his fans (i.e., the deviant Marlians) that imitate and idolise him. Although a few texts on Naira Marley exist, none focus on deviance and moral panics. Following debates on and around social reactions to popular music’s subcultural morality, we discuss the politics of nonconformity and anti-establishmentarian music production in Nigeria and contend that while the moral judgement of Marley’s music content is relative, its deviant mannerism is structurally functional. In other words, the music creates moral panics and advocates social change because its seemingly deviant themes resonate with economically disadvantaged Nigerians who patronise it as a form of escapism.

Editors’ Note

Editors’ Note

On the Development and Practice of AI Technology for Contemporary Popular Music Production

Although the use of AI technology for music production is still in its infancy, it has the potential to make a lasting impact on the way we produce music. In this paper we focus on the design and use of AI music tools for the production of contemporary Popular Music, in particular genres involving studio technology as part of the creative process. First we discuss how music production practices associated with those genres can differ significantly from traditional views of how a musical work is created, and how this affects AI music technology. We argue that—given the role of symbolic representations in this context, as well as the integration of composition activities with editing and mixing—audio-based AI tools are better suited to support the artist’s creative workflow than purely piano-roll/MIDI-based tools. Then we give a report of collaborations with professional artists, in which we look at how various AI tools are used in practice to produce music. We identify usage patterns as well as issues and challenges that arise in practical use of the tools. Based on this we formulate some recommendations and validation criteria for the development of AI technology for contemporary Popular Music.

Right to remix: ideas and original forms of musical works

The modern stage of development of creativity is characterized by an increase in the manufacturability of this type of activity. The art of making popular music fits into this trend, highlighting its advantages and disadvantages most vividly. The peculiarity of popular music production is the repetition of standard expressive means, which have proven to be attractive. The copying of popular fragments and spectacular musical techniques became widespread, resulting in the formation of sound remix culture. Against this background, the number of disputes over the boundaries of legal borrowing of musical material has increased in the courts both in Russia and abroad. In the media sphere, examples of unlawful appropriation of fragments from popular songs that violate the rights of their composers, performers, and producers of phonograms are discussed. To resolve such disputes, specialized procedures have been developed, the results of which are criticized. This article discusses various approaches to the legal qualification of copying musical material. The phenomenon of the formation of musical standards, repetitive elements, techniques, and clichés, which are proposed to be classified as unguarded musical ideas at the doctrinal level, is investigated. The methods used to establish copyright infringement, to identify the facts of unlawful appropriation of musical material, and significant similarity of works are analyzed. Our attention is drawn to the test of the unique quality of a musical work and its justification from the point of view of the principles of copyright. To make decisions on music copying cases, we propose to use data on the quantitative ratio of protected and unprotected material in the compared works, as well as on the sources of borrowing that can be obtained using computer music recognition tools

Disperse and Preserve the Perverse: How Hip-Hop Censorship Changed Popular Music Production in China

How do states censor an artistic genre that challenges the social norms? The answers to this question in the existing literature are mostly based on investigations of particular artists or artworks of the genre, while the impact on the entire genre field remains unchecked. This paper explores how censorship of an artistic genre changes artistic forms of that genre while also triggering strategic reactions from the artists of closely related genres. Using an original dataset of 53,364 songs released on a Chinese online music platform, I study the impact of Hip-Hop censorship in China in 2018 on Hip-Hop as well as Pop, Rock, and Folk songs in terms of how they sound and what topics they write about in the lyrics. I propose a novel approach to measuring sound similarities and topic prevalence in song lyrics using computational tools including Music Information Retrieval (MIR), neural networks, and topic models. I found that Hip-Hop songs produced after the censorship sound significantly different from those before, with a bigger impact on popular songs than unpopular ones. Moreover, genres of similarly restricted production sound more like Hip-Hop after the censorship, while genres of large-scale production sound less “Hip-Hopy”. The censorship also made Hip-Hop musicians engage less with topics related to violence, smoking, or drinking but more with sexual content in a covered form. The findings thus suggest a model of dispersion in explaining the mechanism of censorship in cultural production.

Idols you can make: The player as auteur in Japan’s media mix

Japan has recently seen an upsurge in idol ikusei (nurturing) games: networked mobile games where one nurtures and produces an idol pop group. These games are a significant part of Japan’s contemporary ‘media mix’, influenced both by virtual pet games and by discourses of nurturing surrounding the production of ‘real’ girl idol groups by male producer-auteur figures. Previous analyses have considered affection for simulated or virtual girl idol figures as a detached longing for stylised characteristics ( moe). This article uses a case study of a mobile game at the centre of the Love Live! girl idol-nurturing simulation franchise to suggest that we cannot only speak of players’ affection for nurturing games’ characters in terms of postmodern disembodiment; we must also consider how in playing idol-nurturing games, players take the place of real male producer-auteur figures in Japanese popular music production, where discourses of gendered nurturing abound.

Virtual auditory reality

This article examines popular music listening in light of recent research in auditory perception and spatial experience, record production, and virtual reality, while considering parallel developments in digital pop music production practice. The discussion begins by considering theories of listening and embodiment by Brandon LaBelle, Eric Clarke, Salomè Voegelin and Linda Salter, examining relations between listening subjects and aural environments, conceptualising listening as a process of environmental ‘inhabiting’, and considering auditory experience as the real-time construction of ‘reality’. These ideas are discussed in relation to recent research on popular music production and perception, with a focus on matters of spatial sound design, the virtual ‘staging’ of music performances and performing bodies, digital editing methods and effects, and on shifting relations between musical spatiality, singer-persona, audio technologies, and listener. Writings on music and virtual space by Martin Knakkergaard, Allan Moore, Ragnhild Brøvig-Hanssen & Anne Danielsen, Denis Smalley, Dale Chapman, Kodwo Eshun and Holger Schulze are discussed, before being related to conceptions of VR sound and user experience by Jaron Lanier, Rolf Nordahl & Niels Nilsson, Mel Slater, Tom Garner and Frances Dyson. This critical framework informs three short aural analyses of digital pop tracks released during the last 10 years - Titanium (Guetta & Sia 2010), Ultralight Beam (West 2016) and 2099 (Charli XCX 2019) - presented in the form of autoethnographic ‘listening notes’. Through this discussion on personal popular music listening and virtual spatiality, a theory of pop listening as embodied inhabiting of simulated narrative space, or virtual story-world, with reference to ‘aural-dominant realities’ (Salter), ‘sonic possible worlds’ (Voegelin), and ‘sonic fictions’ (Eshun), is developed. By examining personal music listening in relation to VR user experience, this study proposes listening to pop music in the 21st century as a mode of immersive, embodied ‘storyliving’, or ‘storydoing’ (Allen & Tucker).

Disperse and Preserve the Perverse: Computing How Hip-Hop Censorship Changed Popular Music Production in China

How do states censor an artistic genre that challenges the social norms? The answers to this question in the existing literature are mostly based on investigations of particular artists or artworks of the genre, while the impact on the entire genre field remains unchecked. This paper explores how censorship of an artistic genre changes artistic forms of that genre while also triggering strategic reactions from the artists of closely related genres. Using an original dataset of 53,364 songs released on a Chinese online music platform, I study the impact of Hip-Hop censorship in China in 2018 on Hip-Hop as well as Pop, Rock, and Folk songs in terms of how they sound and what topics they write about in the lyrics. I propose a novel approach to measuring sound similarities and topic prevalence in song lyrics using computational tools including Music Information Retrieval (MIR), neural networks, and topic models. I found that Hip-Hop songs produced after the censorship sound significantly different from those before, with a bigger impact on songs that were played frequently on the platform than those that were not. Moreover, genres of similarly restricted production, such as Rock, sound more like Hip-Hop after the censorship, while genres of large-scale production, such as Pop, sound less “Hip-Hopy”. The censorship also made Hip-Hop musicians engage less with topics related to violence, smoking, or drinking but more with sexual content in a covered form. The findings thus suggest a model of dispersion in explaining the mechanism of censorship in cultural production.

Learning the ‘tracker’ process: A case study into popular music pedagogy

The ‘tracker’ production process is a modern form of music production agency where top-line songwriters work with music programmers called ‘trackers’, primarily within the confines of the digital audio workstation. In this case, production, songwriting and performance often happen concurrently, and collaboration involves the synthesis of ideas, musical negotiations and expertise in using digital and online technologies. In providing popular music production learning activities that translate to professional contexts, higher education institutions face a number of challenges, particularly where much of the collaboration is undertaken online. This article reports on a cohort of Bachelor of Popular Music students who undertook a tracker process module. Students’ perceptions of ‘engagement’ and ‘learning’ were captured via an assessment item and survey, and a themed analysis indicated that the pedagogy promoted the use of diverse social skills, was highly collaborative, relied both on specialist and non-specialist knowledge, and involved the use of digital and online communications.

Beyond the Mainland: Okinawa, Palimpsestic Geography and Octogenarian Island Idols

ABSTRACT This article explores some features of popular music production by uncovering the palimpsestic geography of Okinawa, and in particular the octogenarian island idols of Kohama that have achieved stardom at home and outside their small island setting. As an island Other on multiple levels of separation beyond the mainland, and imagined in terms of geographic and cultural difference within archipelagic, prefectural, and national imaginaries, the assemblage of identity that embodies locality through the sonic discourse of popular music performance reveals pop simulacra on the one hand yet creative and distinct representation of island identity on the other.

A Study on the Direction of Applied Music Education in the Trend of 21 st Century Digital Music Contents

1988년 서울예술대학에 실용음악과 개설 이래 현재까지 지속적으로 증가하여 실용음악 관련 학과가 전국적으로 76개 학교에 개설되었다. 이러한 증가의 이유는 K-Pop의 글로벌한 성공과도 연계하여 생각해 볼 수 있는데, K-Pop은 성장기 청소년들에게 심리적 안녕감을 주며, 더불어 음악적 재능을 갖고 있는 청소년들로 하여금 대중음악 예술가에 대한 우상화 효과와 동경심을 갖도록 하기 때문이다. 매년 국내 실용음악 관련 학과에서 배출되는 예비 대중음악 인력 공급은 시간이 지날수록 팽창하고 있다. 실용음악 교육은 음악 이론 및 실습과 더불어 미디어 콘텐츠 자체를 직접 생산할 수 있는 기술 교육도 포함하고 있기 때문에 전공자들에게 예술가 양성 측면과 콘텐츠 생각 측면 모두 접근 가능한 환경으로 구성되어 있다. 이는 예술가를 비롯한 사업가 혹은 연계 분야로의 진출 가능성을 내포하고 있다. 그러나 현재의 국재 실용음악 교육은 다양한 가능성의 잠재력을 갖고 있음에도 불구하고 콘텐츠 산업에서 필요한 디지털 기술 트렌드 추이와 산업 현장에서 필요한 역량 교육에서 있어서 다각화와 융합적 훈련은 미진해 보인다. 1980년대 MIDI의 출현은 대중음악 제작 시스템과 음악 산업의 큰 변화를 가져왔으며, 개인이 혼자서도 충분히 음악을 제작할 수 있는 시스템이 가능하도록 하였다. 21세기로 진입하면서, 음악시장은 디지털 시대로 완전히 정착을 하였고, 디지털 오디오 형식은 음악 공유의 새로운 시장 패러다임을 만들었다. IT 기술의 진보는 멀티미디어 콘텐츠 시장 활성화를 더욱 부추겼으며, 기술의 발전은 오디오 포맷과 녹음 기술에도 영향을 미치게 된다. 소비자들은 기존의 2채널 스테레오에서 5.1채널, 7.1채널, 바이노럴 녹음 등의 서라운드 음향 경험을 하게 되었고, 이는 음악 콘텐츠 제작의 방법 변화를 가져오게 된다. 기술의 진보에 따라 예술과 과학의 융합 교육이 필요하며, 정통적인 음악 교육을 통한 예술가 배출뿐만 아니라, 연계학문으로의 진출과 사업가 정신이 함양할 필요가 있다. 국내 대학에서 이런 융합 연구를 하는 사례들을 찾아볼 수 있는데, 국내의 일부 대학에서는 음악 교육 이외에 창의, 문제해결, 창업, 글로벌 역량 등의 과정을 포함하는 경우를 발견할 수 있었으며, 해외 대학에서는 미국의 CCRMA, 프랑스의 IRCAM 등의 사례에서 매우 적극적인 예술과 과학 융합 연구가 진행되고 있음을 확인하였다. 매년 수천 명에 이르는 실용음악 계열 전공 졸업자들은 이미 한국 사회에서 과포화 상태에 이르렀으며, 관련 직업은 제한되어 있기 때문에 경제활동을 위한 사회진출이 쉽지 않다. 정통 음악 교육 방식을 벗어나 음악 창의적 능력을 융합한 사업가 그리고 과학자를 배출할 수 있는 다각적 사고의 폭을 넓히도록 도움을 줄 수 있는 실용음악 교육 패러다임의 전환이 필요하다.Since the Department of Applied Music at Seoul Institute of the Arts opened in 1988, 76 applied music schools has been opened, nationwide. The reason may be connected to K-Pop’s global success, which promotes the psychological well-being of the youth, and the idolization of pop artists. This is because it has an effect and a longing. Preliminary human resources produced by domestic applied music-related departments for the pop music industry is growing every year. In addition to music theory and practice, applied music education includes technical education to produce media contents directly. This implies the possibility of entry as artists, entrepreneurs, etc. Although the current Korean applied music education has the potential to explore various possibilities, diversification and convergence training seem to be insufficient with respect to the requirements of digital technology in the contents industry and competency education in the industrial field. The emergence of Musical Instrument Digital Interface(MIDI) in the 1980s brought a major change in the popular music production system and the music industry, enabling individuals to produce music themselves. As we entered the 21st century, the music market settled completely into the digital age, and digital audio formats created a new market paradigm for music sharing. Advancements in Information Technology have further fueled the growth of multimedia contents market. They are affecting audio formats and recording technologies. Additionally, consumers have already experienced a surround sound effect of 5.1ch, 7.1ch, binaural recordings, etc., on existing 2ch stereos, which is changing the way music contents are being produced. Technological advancements call for art and science convergence education. Artists not only require the usual music education, but they also need skills to advance into connected studies and cultivate their business spirit. Examples of such convergence research are found at domestic universities. Some universities in Korea include music, education, problem solving, entrepreneurship, and global competency. With respect to overseas educational institutions such as Stanford Center for Computer Research in Music and Acoustics(CCRMA) in the USA and Institute for Research and Coordination in Acoustics/Music(IRCAM) in France, it is found that research on art and science convergence is already in progress. Korea produces thousands of applied music graduates each year, resulting in oversaturation of the market. Hence, their careers are limited and so are their opportunities to get involved in economic activities. Applied music education will experience a shift in the paradigm that can help in expanding the multifaceted thinking required to produce entrepreneurs and scientists who have creative converged music skills beyond knowledge acquired from typical music education methods.

Artificial Intelligence & Popular Music: SKYGGE, Flow Machines, and the Audio Uncanny Valley

This article presents an overview of the first AI-human collaborated album, Hello World, by SKYGGE, which utilizes Sony’s Flow Machines technologies. This case study is situated within a review of current and emerging uses of AI in popular music production, and connects those uses with myths and fears that have circulated in discourses concerning the use of AI in general, and how these fears connect to the idea of an audio uncanny valley. By proposing the concept of an audio uncanny valley in relation to AIPM (artificial intelligence popular music), this article offers a lens through which to examine the more novel and unusual melodies and harmonization made possible through AI music generation, and questions how this content relates to wider speculations about posthumanism, sincerity, and authenticity in both popular music, and broader assumptions of anthropocentric creativity. In its documentation of the emergence of a new era of popular music, the AI era, this article surveys: (1) The current landscape of artificial intelligence popular music focusing on the use of Markov models for generative purposes; (2) posthumanist creativity and the potential for an audio uncanny valley; and (3) issues of perceived authenticity in the technologically mediated “voice”.

Popular music education: A white paper by the Association for Popular Music Education

Abstract In this white paper, board members of the Association for Popular Music Education set out practices, approaches and domains that account for popular music education as understood in the present moment in largely English-speaking contexts. Popular music education has come of age as a field, overlapping with fields including popular music studies, music education, music business, music technology and music production, community music, media studies, ethnomusicology and communication studies. Popular music education is diverse and inclusive. It also has deep commercial and industrial connections. It includes school teaching, music teacher education and Higher music education. Popular music education scholarship and practice are expanding. The authors invite responses to this white paper in order to engender discussion and curate a community of practitioners and scholars.