Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Neural Computing and Applications
Erschienen in: Neural Computing and Applications 4/2020

15.10.2018 | Deep learning for music and audio

Towards a Deep Improviser: a prototype deep learning post-tonal free music generator

verfasst von: Roger T. Dean, Jamie Forth

Erschienen in: Neural Computing and Applications | Ausgabe 4/2020

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Two modest-sized symbolic corpora of post-tonal and post-metrical keyboard music have been constructed: one algorithmic and the other improvised. Deep learning models of each have been trained. The purpose was to obtain models with sufficient generalisation capacity that in response to separate fresh input seed material, they can generate outputs that are statistically distinctive, neither random nor recreative of the learned corpora or the seed material. This objective has been achieved, as judged by k-sample Anderson–Darling and Cramer tests. Music has been generated using the approach, and preliminary informal judgements place it roughly on a par with an example of composed music in a related form. Future work will aim to enhance the model such that it deserves to be fully evaluated in relation to expression, meaning and utility in real-time performance.
Vorheriger Artikel This time with feeling: learning expressive musical performance
Nächster Artikel Deep learning for music generation: challenges and directions

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Chew E (2005) Regards on two regards by Messiaen: post-tonal music segmentation using pitch context distances in the spiral array. J New Music Res 34(4):341–354CrossRef
2.
Dean RT, Pearce MT (2016) Algorithmically-generated corpora that use serial compositional principles can contribute to the modeling of sequential pitch structure in non-tonal music. Empir Musicol Rev 11(1):27–46CrossRef
3.
Jost E (1974) Free jazz, English edn. Universal, Graz
4.
Bailey D (1992) Improvisation, its nature and practice in music, revised edition. British Library (first published 1980), London
5.
Pressing J (2002) Free Jazz and the avant-garde. In: Cooke M, Horn D (eds) The Cambridge companion to jazz. Cambridge University Press, Cambridge, pp 202–216
6.
Smith H, Dean RT (1997) Improvisation, hypermedia and the arts since 1945. Routledge, London
7.
Dean RT, Bailes F, Drummond J (2014) Generative structures in improvisation: computational segmentation of keyboard performances. J New Music Res 43(2):224–236CrossRef
8.
Dean RT, Bailes F (2016) Relationships between generated musical structure, performers’ physiological arousal and listener perceptions in solo piano improvisation. J New Music Res 45(4):361–374CrossRef
9.
Beaty RE (2015) The neuroscience of musical improvisation. Neurosci Biobehav Rev 51:108–117CrossRef
10.
11.
Vuust P, Kringelbach ML (2017) Music improvisation: a challenge for empirical research. In: Ashley R, Timmers R (eds) Routledge companion to music cognition. Routledge, New York, pp 265–275CrossRef
12.
Rowe R (1993) Interactive music systems. Machine listening and composing. MIT Press, Cambridge
13.
Lewis GE (2000) Too many notes: computers, complexity and culture in voyager. Leonardo Music J 10:33–39CrossRef
14.
Dean RT (2003) Hyperimprovisation: computer interactive sound improvisation; with CD-Rom. A-R Editions, Madison
15.
Edwards M (2011) Algorithmic composition: computational thinking in music. Commun ACM 54(7):58–67CrossRef
16.
Herremans D, Chuan C-H, Chew E (2017) A functional taxonomy of music generation systems. ACM Comput Surv (CSUR) 50(5):61-33CrossRef
17.
Nierhaus G (2009) Algorithmic composition: paradigms of automated music generation. Springer, New YorkCrossRef
18.
Pachet F (2003) The continuator: musical interaction with style. J New Music Res 32(3):333–341CrossRef
19.
Dean RT (2017) Generative live music-making using autoregressive time series models: melodies and beats. J Creat Music Syst 1(2):1–19
20.
Chollet F (2017) Deep learning with python. Manning Electronic Advanced Publication, Shelter Island
21.
22.
McLean A, Dean RT (2018) The Oxford handbook of algorithmic music. Oxford University Press, New York
23.
Fernández JD, Vico F (2013) AI methods in algorithmic composition: a comprehensive survey. J Artif Intell Res 48:513–582MathSciNetCrossRef
24.
Colombo F, Muscinelli SP, Seeholzer A, Brea J, Gerstner W (2016) Algorithmic composition of melodies with deep recurrent neural networks. arXiv:​160607251
25.
Mehri S, Kumar K, Gulrajani I, Kumar R, Jain S, Sotelo J, Courville A, Bengio Y (2016) SampleRNN: an unconditional end-to-end neural audio generation model. arXiv:​161207837
26.
Engel J, Resnick C, Roberts A, Dieleman S, Eck D, Simonyan K, Norouzi M (2017) Neural Audio synthesis of musical notes with WaveNet autoencoders. arXiv:​170401279
27.
Sturm BL, Ben-Tal O (2017) Taking the models back to music practice: evaluating generative transcription models built using deep learning. J Creat Music Syst 2(1):27
28.
29.
30.
Dean RT, Smith H (2018) The character thinks ahead: creative writing with deep learning nets and its stylistic assessment. Leonardo 1–2 (online, just accepted)CrossRef
31.
Dean RT, Bailes F (2010) Time series analysis as a method to examine acoustical influences on real-time perception of music. Empir Musicol Rev 5:152–175CrossRef
32.
Serra J, Kantz H, Serra X, Andrzejak RG (2012) Predictability of music descriptor time series and its application to cover song detection. IEEE Trans Audio Speech Lang Process 20(2):514–525
33.
Gingras B, Pearce MT, Goodchild M, Dean RT, Wiggins G, McAdams S (2016) Linking melodic expectation to expressive performance timing and perceived musical tension. J Exp Psychol Hum Percept Perform 42(4):594–609CrossRef
34.
Enders W (2004) Applied econometric time series, 2nd edn. Wiley, Hoboken
35.
Madjiheurem S, Qu L, Walder C Chord2Vec: learning musical chord embeddings. In: Proceedings of the constructive machine learning workshop at 30th conference on neural information processing systems (NIPS’2016), Barcelona, Spain, 2016, paper 5, pp 1–5
36.
Pressing J (1987) The micro-and macrostructural design of improvised music. Music Percept 5(2):133–172CrossRef
37.
Herremans D, Chuan C-H (2017) Modeling musical context using Word2vec. In: First international workshop on deep learning and music, pp 11–18
38.
Pearce M, Wiggins G (2001) Towards a framework for the evaluation of machine compositions. In: Proceedings of the AISB’01 symposium on artificial intelligence and creativity in the arts and sciences, Citeseer, pp 22–32
39.
Jordanous A (2012) A standardised procedure for evaluating creative systems: computational creativity evaluation based on what it is to be creative. Cogn Comput 4(3):246–279CrossRef
40.
Agres K, Forth J, Wiggins GA (2016) Evaluation of musical creativity and musical metacreation systems. Comput Entertain 14(3):1–35CrossRef
41.
Lamb C, Brown D, Clarke C (2017) Incorporating novelty, meaning, reaction and craft into computational poetry: a negative experimental result. In: Proceedings of 8th international conference on computational creativity, ICCC
42.
Wiggins GA, Forth J (2017) Computational creativity and live algorithms. In: McLean A, Dean RT (eds) The Oxford handbook of algorithmic music. Oxford University Press, New York (in press, 2018)
43.
Pearce MT, Wiggins GA (2006) Expectation in melody: the influence of context and learning. Music Percept 23:377–405CrossRef
44.
Forth J, Wiggins GA (2009) An approach for identifying salient repetition in multidimensional representations of polyphonic music. In: Chan J, Daykin JW, Sohel Rahman M (eds) London algorithmics 2008. College Publications, London, pp 44–58
45.
Forth J, Wiggins GA, McLean A (2010) Unifying conceptual spaces: concept formation in musical creative systems. Mind Mach 20(4):503–532CrossRef
46.
Wiggins GA, Forth J (2015) IDyOT: a computational theory of creativity as everyday reasoning from learned information. In: Besold TR, Schorlemmer M, Smaill A (eds) Computational creativity research: towards creative machines. Springer, New York, pp 127–148
47.
Forth J, Agres K, Purver M, Wiggins GA (2016) Entraining IDyOT: timing in the information dynamics of thinking. Front Psychol 7(1575):1–19
Metadaten
Titel
Towards a Deep Improviser: a prototype deep learning post-tonal free music generator
verfasst von
Roger T. Dean
Jamie Forth
Publikationsdatum
15.10.2018
Verlag
Springer London
Erschienen in
Neural Computing and Applications / Ausgabe 4/2020
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-018-3765-x

Weitere Artikel der Ausgabe 4/2020

Neural Computing and Applications 4/2020 Zur Ausgabe

Review Article

Bat algorithm-based weighted Laplacian probabilistic neural network

Editorial

The emergence of deep learning: new opportunities for music and audio technologies

Deep learning for music and audio

One deep music representation to rule them all? A comparative analysis of different representation learning strategies

Deep learning for music and audio

Exploiting time-frequency patterns with LSTM-RNNs for low-bitrate audio restoration

Deep learning for music and audio

This time with feeling: learning expressive musical performance

Original Article

A disaster relief operations management model: a hybrid LP–GA approach