Tag Archive for: classic music

Machine-Learning Methods for Analysis and Generation of Expressive Performance

Artificial Intelligence and Machine Learning are some of the leading technology trends in the global scene, due to the easy access to big data technologies that store and analyse data, such as Apache Hadoop, Microsoft HDInsight, NoSQUL, among others. The large amount of data keeps raising and accumulating each year, which pave the way for the analysis of massive amounts of collected data in the future.

Today, anyone with basic knowledge can start using these new technological opportunities that offer great advantages lowering the price of storage, using open source solutions (without any license fees) and constantly improving these technologies to be more accessible. In the last years, a storm of hype hit the marked, initially with Cloud Computing, then Big Data, Internet of things (IOT), following many more. But now, we are in the verge of transforming these massive amount of data into valuable information, and even more, not only we humans can get new insights to learn and improve things, but machines can do that for us, in a massive scale.

Digitalizing everything

Thanks to IOT and Big Data technologies, we are able to hold more data than ever before. This has an extraordinary value especially when the volume of data is huge. IOT technologies are capable to obtain sensor data in an extremely easy and affordable way.

Big Data Systems are attracting the interest of a growing number of Data Scientists, producing new research with limitless possibilities. Some of them are finding a whole new greenfield in the analysis of human behaviour through computational algorithms that reveal patterns in order to predict and understand how our society works. An interesting example is the so-called “mathematics of love”. Although it could be thought love to be the last thing on earth that someone could imagine to digitalize and predict, based on data, we could actually find recognizable and quantifiable patterns on love, human feelings and human behaviours. When we analyse a discreet amount of people, we have no guarantees that this might apply to another group, but when we use a massive amount of data, we can start raising up our odds when predicting or understanding, an ethereal thing, such as Love.

Learning from patterns

Now, we have got into a point, that almost any cognitive science could be transposed into quantifiable patterns. The information could be systematically extracted using a machine that would assist researchers in recognizing specific insights that probably would pass unnoticed by humans. And, certainly, this new technology could also be applicable to the field of performing arts.

The analysis of massive amounts of data using computer software not only can save years of laborious human research, but also might produce results that are more accurate and objective than time other consuming traditional approaches. According, this new technology might imply transforming traditional methods used by researchers. [1] For example, developing a software that generates expressive interpretations played in a historically appropriate manner would revolutionize the approach to early music performance.

Currently, the main trends in computational systems for music performance includes the use of data-driven (machine learning) methods for analysis and generation of expressive performance, expressive interactive systems and cognitive models. The KTH model built by the KTH Royal Institute of Technology in Stockholm, is one of the most successful approaches in the generation of piano performances. It is built using a rule-based methodology in which performance patterns are set manually, as opposed to data-driven methods in which musical patterns are detected from large databases of music scores and performances. [2]

Generating Human performances

But, is the machine really able to emulate human expressive music performances? Although, there have been some brilliant attempts to produce piano performances with computer technologies, the outcomes are distant to be satisfactory from an artistic point of view. This is not surprising at all considering that usually research on music performances rendered by the machine is carried by teams formed mainly by computer experts, with only but a little input from music scientists. For this reason, although some renditions might sound convincing to some listeners, they still do not suffice the exigencies of professionally trained musicians. In order to produce research that is meaningful in the field of performing arts, it is essential to apply musicological methods and historical appropriate approaches to understand the music aesthetics of different historical periods. For example, in order to teach the machine to perform like legendary pianists from 19th and 20th-century, it would be ideal to define expressive patterns from a large corpus of early recordings, in particular piano roll digitalisations. Extractions from CD recordings by pianists does not offer the same accuracy as Musical Instrument Digital Interface (MIDI) recordings. Piano rolls can be converted to Performance data MIDI files data using a pneumatic interface such as the pneumatic roll reader that digitalises the human expression captured on the rolls. [3] In order to achieve this goal, it is essential an in-depth investigation on reproducing mechanical systems and methodologies for the extraction and categorisation of music parameters. [4]

Music scientists’ contribution not only adds artistic value to the performance rendering but also musicological knowledge and historical accuracy. It would also contribute to advance research in embodied cognition generating expressive music performance using historically appropriate sources, and embodying performing practices using computational models. This will lead towards the transformation of historical informed performance (HIP), developing and implementing a new methodological practice-led cyclical research, combining musicological research and artificial intelligence. In so doing, it will further expertise in exploring long term musical structures in the production of meaningful interpretations, which is currently understudied due to its complexity.

Learning to play like the masters

Algorithmic calculations of expressive patterns can be developed to generate human performance. Teaching the machines different piano techniques with relative accuracy could also have a significant impact as an educational tool. It would be possible to emulate a specific music style, comparing early performance practices to our modern interpretations. It could be used to compare pianists by nationality, age, pianistic tradition, even it could be used to compare human aspects such as difference in playing according to age or gender. Furthermore, it could be also used as a piano teacher that is able to identify the student’s skill level and musical style, in this way the students could easily assess their own pianistic technique and stylistic accuracy.

Once, we can quantify and identify such human expressions, the resources to learn from it are limitless, and therefore, we will answer questions that we could never had answered before and raise new questions that we never thought of.


References

[1] Performance-based research that develops a new practice-led approach assisted by computational technologies and digitalised sources in the study of performance see Carolina Estrada Bascuñana “New Approaches to Enrique Granados’ Pedagogical Methods and Pianistic Tradition: A Case of Study of Valses poéticos op. 43,” in Diagonal: An Ibero-American Music Review, 2(1), http://dx.doi.org/10.5070/D82135899 Retrieved from https://escholarship.org/uc/item/3z711898 (last accessed 9 December 2019)

[2] For a detailed critical review of current methods see Cancino-Chacón, Carlos Eduardo, Maarten Grachten, Werner Goebl, and Gerhard Widmer “Computational models of expressive music performance: A comprehensive and critical review,” in Frontiers in Digital Humanities 5 (2018): 25, http://frontiersin.org/articles/10.3389/fdigh.2018.00025/full

[3] A discussion of optical and pneumatic technologies and methods for archiving piano rolls is presented in Peter Phillips, “Piano Rolls and Contemporary Player Pianos: The Catalogues, Technologies, Archiving and Accessibility”, (University of Sydney, 2017), https://ses.library.usyd.edu.au/handle/2123/16939 (last accessed 9 December 2019).

[4] Concerning issues and mechanical limitations in the analysis of recordings captured on reproducing systems see Carolina Estrada Bascuñana “Enrique Granados’s Performance Style: Visualising the Audible Evidence,” in: Rund um Beethoven.Interpretationsforschung heute, ed. By Thomas Gartmann and Daniel Allebach, Schliengen: Argus 2019 (Musikforschung der Hochschule der Künste Bern, vol. 14), p. 150–179, https://www.hkb-interpretation.ch/fileadmin/user_upload/documents/Publikationen/Bd.14/HKB14_Rund_um_Beethoven.pdf (last accessed 9 December 2019)

Creative Commons LicenceCreate PDF

Related Posts

None found

Contemporary Classical Music and the Digital Transformation of Society

Contemporary classical music is a fascinating showcase for the impact of digital transformation. Apart from that, it helps us to direct our thoughts to the future, wrotes our author Reinhard Riedl.

Contemporary classical music, in German either “Neue Musik” or “neue Musik”, is permanently changing and, as is the case for many arts, these changes correspond to changes in society. Nearly all these changes meet with clear rejection or disparagement, but eventually they nevertheless gain the acceptance of the music community’s more knowledgeable members. Although this often takes decades.

Contemporary aesthetics pointing towards the future

Looking at the many dystopian stories about digital transformation raises the question of what we can learn from contemporary classical music for our research on digital transformation. If we compare the history of N/neue Musik with the history of management, music is 50, 100, even 1000 years ahead of management. It is already quite some time ago that composers taught us the hard way that an educated and anticipating ear is not good enough to grasp the essence of a piece of music. We really need to listen permanently and carefully. But so far only a few Elitists have broadly established the virtue of truly listening to their customers. In addition, collaboration in industry and in government is of far worse quality than the collaboration of orchestras playing any classical music, simply because experts and managers are badly trained in listening to their peers, and many leaders listen only very selectively to their subordinates. Rather, many business leaders act like conductors who only focus on one section in the orchestra, usually with devastating consequences for the overall performance. In business, it seems, such effects do not have much relevance yet.

Silence is another traditional “theme” from contemporary classical music (1) that is about to enter the business world, where it can be purposely used to manufacture morals (2). Other aesthetical qualities can only be guessed to have key relevance for future business. For example, the composers Beat Furrer leads the listener to realms of immense emptiness, timelessness, and absence of future which sensitizes the listener’s perception for the richness of the phenomenon of “sound fading away” – a vague forecast of future extreme forms of business that we still find hard to imagine. The specific quality of presence in performed music, respectively of hic et nunc, is the resounding and fading away of sound. It becomes an extremely intense experience in many pieces of N/neue Musik and it can be seen as a counterpart to the “normal” inflation of presence in our lives, that is the loss of history and future in contemporary consumer society(3). The composer John Cage has exported of the aesthetics of presence to experimental literature (4), and postdramatic theatre has developed artificially authentic practices to playfully celebrate pure presence. Thus, N/neue Musik from a few decades ago teaches us a lot about leadership in avantgarde companies, while truly contemporary compositions may shed light on a so far widely unknown future of business, government, and society.

The digital transformation of contemporary classical music

Let us investigate in more depth the digitalization of composing observed in contemporary composition practices. These days contemporary classical music is challenged by digitalization. Software enables near arbitrary design of music. Experiments without much thought may easily lead to the creation of alluring music by accident rather than by design. Thereby, algorithms both serve and deafen the composers as they shape synthesized musical surfaces with and without substance. This creates a kind of neue Musik 4.0, for which listening is even more critical than for traditional Neue Musik, because the software capabilities are forcing the audience to listen through the computational surface of digitally created music. Thereby it is very unclear who is wrestling more with the algorithmic composition software, the composer who must defend the independence of her thoughts against the dominance of the software’s algorithms or us who listen to the music in concert. To regain artistic autonomy, some musicians only use custom-made software that is coded to specifically support their clear intentions. Thus, contemporary classical music has become a showcase of what will happen in the future digital transformation of our lives, pointing us to practices that can help us defending a bit of our autonomy.

Escaping the dangers of digitalization is hardly an option, because man-machine collaboration exploiting artificial intelligence to create music will soon become a standard – all the more when it is no longer detectable as such. True, there have been lots of rather pointless attempts to create fake new pieces of long dead composers. However, the merger between computing power and artistic thought is a step beyond all such experiments: It leads to digitally enabled composing which is truly new. Furthermore, there are lots of ways to invent new forms of digitally enabled performance practices, for example it is now possible to measure the audience’s biodata to adapt the score presented to the musicians. And many more freaky setups are waiting around the corner. Not to mention the myriad things we can do to traditional music that is traditionally performed, such as recording performances from arbitrary positions inside instruments, or supporting the preparation work of the conductor through virtually arranged performances. Thus, although the contemporary classical music will not help to predict economic changes, it has a significant potential to showcase how digital transformation will work.

Omitting the digital enabling of artistic work in research on digital transformation is like searching for innovation by excluding the most creative options. Music has a long history of early technology adoption. We should exploit this – both to study the impact of digitalization and to run funky digitalization experiments. So far, we lack theoretical foundations for such studies. However, rereading Jacques Rancière (5) with the mind of an applied computer scientists or an engineering economist may help to link aesthetic practices in contemporary classical music to contemporary digital design practices.

History

In 1922 the International Society for Contemporary Music was founded in Salzburg as Internationale Gesellschaft für eue Musik (IGNM). It has chapters in many countries all over the world. Remarkably enough, the Salzburg Festival later became long time famous for its ignorance of contemporary classical music. Nowadays, however, the Salzburg Festival is again one of the places to listen to new music – both because of the excellence of curation and of the performing ensembles and because of the intense interest of the audience.

IGNM BERN

In 2005, the “Konzertgesellschaft Neue Horizonte” became IGNM Bern and thus part of the traditional global network. Its mission is to import new music to Bern, to promote and curate contemporary composers, to bring the societal discourse to contemporary classical music, to take up specific societal challenges, and to create highly different but aesthetically unique experiences for the audience. The program is currently based on a 4-topic theme, “Belonging” & “Pure Corporality” & “Extended Identities” & “Mix & Match”, which reflects trends in society. There are seven different nationalities represented in the local board of IGNM Bern (6), and many curated music ensembles come from abroad. In the case of concerts touching on socially relevant topics, these concerts are accompanied by a panel discussion or a scientific or philosophical talk. Such as the IGNM concert “Wrestling the Algorithm” (7) which addressed the role of algorithms in music and society


Referenzen

  1. 4’33, Wikipedia
  2. Michel Anteby, Manufacturing Morals: The Values of Silence in Business Education, University of Chicago Press, 2013
  3. Guillaume Paoli, Die lange Nacht der Metamorphose – Über die Gentrifizierung der Kultur, Matthes & Seitz Berlin, 2017
  4. John Cage, Silence, 1961
  5. Jacques Rancière, The Politics of Aesthetics: The Distribution oft he Sensible (English translation by Gabriel Rockhill), 2004
  6. www.ignm-bern.ch
  7. Simon Mathis, Die Digitalisierung transformiert auch die Musik, Netzmedien, 2017
Creative Commons LicenceCreate PDF

Related Posts

None found