Skip to main content
Erschienen in: Neural Processing Letters 3/2020

09.06.2020

A Style-Specific Music Composition Neural Network

verfasst von: Cong Jin, Yun Tie, Yong Bai, Xin Lv, Shouxun Liu

Erschienen in: Neural Processing Letters | Ausgabe 3/2020

Einloggen

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

search-config
loading …

Abstract

Automatic music composition could dramatically decrease music production costs, lower the threshold for the non-professionals to compose as well as improve the efficiency of music creation. In this paper, we proposed an intelligent music composition neutral network to automatically generate a specific style of music. The advantage of our model is the innovative structure: we obtained the music sequence through an actor’s long short term memory, then fixed the probability of sequence by a reward-based procedure which serves as feedback to improve the performance of music composition. The music theoretical rule is introduced to constrain the style of generated music. We also utilized a subjective validation in experiment to guarantee the superiority of our model compared with state-of-the-art works.

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

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!

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!

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!

Literatur
1.
Zurück zum Zitat van der Zwaag MD, Janssen JH, Westerink JHDM (2013) Directing physiology and mood through music: validation of an affective music player. IEEE Trans Affect Comput 4(1):57–68CrossRef van der Zwaag MD, Janssen JH, Westerink JHDM (2013) Directing physiology and mood through music: validation of an affective music player. IEEE Trans Affect Comput 4(1):57–68CrossRef
2.
Zurück zum Zitat Li Z, Tang J, Mei T (2019) Deep collaborative embedding for social image understanding. IEEE Trans Pattern Anal Mach Intell 41(9):2070–2083CrossRef Li Z, Tang J, Mei T (2019) Deep collaborative embedding for social image understanding. IEEE Trans Pattern Anal Mach Intell 41(9):2070–2083CrossRef
3.
Zurück zum Zitat Li Z, Tang J (2015) Weakly supervised deep metric learning for community-contributed image retrieval. IEEE Trans Multimed 17(11):1989–1999CrossRef Li Z, Tang J (2015) Weakly supervised deep metric learning for community-contributed image retrieval. IEEE Trans Multimed 17(11):1989–1999CrossRef
4.
Zurück zum Zitat Margounakis D, Politis D (2012) Science of networking: new trends in music production, distribution and management. In: Proceedings of international conference on information society, London, pp 486–491 Margounakis D, Politis D (2012) Science of networking: new trends in music production, distribution and management. In: Proceedings of international conference on information society, London, pp 486–491
5.
Zurück zum Zitat Fernández JD, Vico F (2013) AI methods in algorithmic composition: a comprehensive survey. J Artif Intell Res 48:513–582MathSciNetCrossRef Fernández JD, Vico F (2013) AI methods in algorithmic composition: a comprehensive survey. J Artif Intell Res 48:513–582MathSciNetCrossRef
8.
Zurück zum Zitat Yan M, Chan CA, Gygax AF, Yan J, Campbell L, Nirmalathas A, Leckie C (2019) Modeling the total energy consumption of mobile network services and applications. Energies 12(1):184CrossRef Yan M, Chan CA, Gygax AF, Yan J, Campbell L, Nirmalathas A, Leckie C (2019) Modeling the total energy consumption of mobile network services and applications. Energies 12(1):184CrossRef
9.
Zurück zum Zitat Li Z, Tang J (2015) Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans Image Process 24(12):5343–5355MathSciNetCrossRef Li Z, Tang J (2015) Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans Image Process 24(12):5343–5355MathSciNetCrossRef
11.
Zurück zum Zitat Balaban M, Ebcioglu K, Laske O (1992) Understanding music with AI: perspectives on music cognition. In: AAAI Press, pp 186–205 Balaban M, Ebcioglu K, Laske O (1992) Understanding music with AI: perspectives on music cognition. In: AAAI Press, pp 186–205
12.
Zurück zum Zitat Ebcioglu K (1990) An expert system for harmonizing chorales in the style of J. S. Bach. J Log Program 8(1–2):145–185MathSciNetCrossRef Ebcioglu K (1990) An expert system for harmonizing chorales in the style of J. S. Bach. J Log Program 8(1–2):145–185MathSciNetCrossRef
13.
Zurück zum Zitat Biles JA (1994) GenJam: a genetic algorithm for generating jazz solos. ICMA 94:131–137 Biles JA (1994) GenJam: a genetic algorithm for generating jazz solos. ICMA 94:131–137
16.
Zurück zum Zitat Hadjeres G, Pachet F, Nielsen F (2017) Deepbach: a steerable model for bach chorales generation. In: Proceedings of ICML, pp 1362–1371 Hadjeres G, Pachet F, Nielsen F (2017) Deepbach: a steerable model for bach chorales generation. In: Proceedings of ICML, pp 1362–1371
18.
Zurück zum Zitat Akbari M, Liang J (2018) Semi-recurrent CNN-based VAE–GAN for sequential data generation. In: Proceedings of ICASSP, pp 2321–2325 Akbari M, Liang J (2018) Semi-recurrent CNN-based VAE–GAN for sequential data generation. In: Proceedings of ICASSP, pp 2321–2325
19.
Zurück zum Zitat Roberts A, Engel J, Raffel C, Hawthorne C (2018) A hierarchical latent vector model for learning long-term structure in music. In: Proceedings of ICML Roberts A, Engel J, Raffel C, Hawthorne C (2018) A hierarchical latent vector model for learning long-term structure in music. In: Proceedings of ICML
20.
Zurück zum Zitat Brunner G, Konrad A, Wang Y, Wattenhofer R (2018) MIDI-VAE: modeling dynamics and instrumentation of music with applications to style transfer. In: Proceedings of ISMIR Brunner G, Konrad A, Wang Y, Wattenhofer R (2018) MIDI-VAE: modeling dynamics and instrumentation of music with applications to style transfer. In: Proceedings of ISMIR
21.
Zurück zum Zitat Yang L-C, Chou S-Y, Yang Y-H (2017) MidiNet: a convolutional generative adversarial networks for symbolic-domain music generation. In: Proceedings of ISMIR Yang L-C, Chou S-Y, Yang Y-H (2017) MidiNet: a convolutional generative adversarial networks for symbolic-domain music generation. In: Proceedings of ISMIR
22.
Zurück zum Zitat Dong HW, Hsiao WY, Yang LC, Yang YH (2018) MuseGAN: symbolic-domain music generation and accompaniment with multitrack sequential generative adversarial networks. In: Proceedings of AAAI Dong HW, Hsiao WY, Yang LC, Yang YH (2018) MuseGAN: symbolic-domain music generation and accompaniment with multitrack sequential generative adversarial networks. In: Proceedings of AAAI
23.
Zurück zum Zitat Yu L, Zhang W, Wang J, Yu Y (2017) SeqGAN: sequence generative adversarial nets with policy gradient. In: Proceedings of AAAI Yu L, Zhang W, Wang J, Yu Y (2017) SeqGAN: sequence generative adversarial nets with policy gradient. In: Proceedings of AAAI
24.
Zurück zum Zitat Brunner G, Wang Y, Wattenhofer R, Zhao S (2018) Symbolic music genre transfer with CycleGAN. In: Proceedings of ICTAI Brunner G, Wang Y, Wattenhofer R, Zhao S (2018) Symbolic music genre transfer with CycleGAN. In: Proceedings of ICTAI
25.
Zurück zum Zitat Zhu X, Zhang S, Hu R, He W, Lei C, Zhu P (2019) One-step multi-view spectral clustering. IEEE Trans Knowl Data Eng 31(10):2022–2034CrossRef Zhu X, Zhang S, Hu R, He W, Lei C, Zhu P (2019) One-step multi-view spectral clustering. IEEE Trans Knowl Data Eng 31(10):2022–2034CrossRef
26.
Zurück zum Zitat van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A (2016) WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A (2016) WaveNet: a generative model for raw audio. arXiv preprint arXiv:​1609.​03499
27.
Zurück zum Zitat Manzelli R, Thakkar V, Siahkamari A et al (2018) Conditioning deep generative raw audio models for structured automatic music. In: Proceedings of ISMIR Manzelli R, Thakkar V, Siahkamari A et al (2018) Conditioning deep generative raw audio models for structured automatic music. In: Proceedings of ISMIR
28.
Zurück zum Zitat Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Proceedings of NIPS, pp 2672–2680 Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Proceedings of NIPS, pp 2672–2680
29.
Zurück zum Zitat Gross R, Gu Y, Li W, Gauci M (2017) Generalizing GANs: a turing perspective. In: Proceedings of NIPS, pp 6316–6326 Gross R, Gu Y, Li W, Gauci M (2017) Generalizing GANs: a turing perspective. In: Proceedings of NIPS, pp 6316–6326
30.
Zurück zum Zitat Grondman I, Busoniu L, Lopes GAD, Babuska R (2012) A survey of actor–critic reinforcement learning: standard and natural policy gradients. IEEE Trans Syst Man Cybern 42(6):1291–1307CrossRef Grondman I, Busoniu L, Lopes GAD, Babuska R (2012) A survey of actor–critic reinforcement learning: standard and natural policy gradients. IEEE Trans Syst Man Cybern 42(6):1291–1307CrossRef
31.
Zurück zum Zitat Li L, Li D, Song T, Xu X (2018) Actor–critic learning control based on regularized temporal-difference prediction with gradient correction. IEEE Trans Neural Netw Learn Syst 29(12):5899–5909CrossRef Li L, Li D, Song T, Xu X (2018) Actor–critic learning control based on regularized temporal-difference prediction with gradient correction. IEEE Trans Neural Netw Learn Syst 29(12):5899–5909CrossRef
32.
Zurück zum Zitat LeCun Y et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551CrossRef LeCun Y et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551CrossRef
33.
Zurück zum Zitat Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRef Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRef
35.
Zurück zum Zitat Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Proceedings of INTERSPEECH, pp 338–342 Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Proceedings of INTERSPEECH, pp 338–342
36.
Zurück zum Zitat Fan Y, Qian Y, Xie F, Soong FK (2014) TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proceedings of INTERSPEECH, pp 1964–1968 Fan Y, Qian Y, Xie F, Soong FK (2014) TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proceedings of INTERSPEECH, pp 1964–1968
37.
Zurück zum Zitat Malandrino D, Pirozzi D, Zaccagnino R (2018) Visualization and music harmony: design, implementation and evaluation. In: Proceedings of 22nd international conference information visualisation, pp 498–503 Malandrino D, Pirozzi D, Zaccagnino R (2018) Visualization and music harmony: design, implementation and evaluation. In: Proceedings of 22nd international conference information visualisation, pp 498–503
38.
Zurück zum Zitat Chiu S, Shan M (2006) Computer music composition based on discovered music patterns. In: Proceedings of IEEE international conference on systems, man and cybernetics, pp 4401–4406 Chiu S, Shan M (2006) Computer music composition based on discovered music patterns. In: Proceedings of IEEE international conference on systems, man and cybernetics, pp 4401–4406
39.
Zurück zum Zitat Chathuranga EADY, Ratnayake HUW, Premaratne IA (2017) An expert system to generate chords for melodies composed in eastern music format. In: Proceedings of international conference on computer, communications and electronics, pp 501–504 Chathuranga EADY, Ratnayake HUW, Premaratne IA (2017) An expert system to generate chords for melodies composed in eastern music format. In: Proceedings of international conference on computer, communications and electronics, pp 501–504
40.
Zurück zum Zitat Mnih V, Kavukcuoglu K, Silver D et al (2013) Playing Atari with deep reinforcement learning. In: Proceedings of NIPS, pp 201–220 Mnih V, Kavukcuoglu K, Silver D et al (2013) Playing Atari with deep reinforcement learning. In: Proceedings of NIPS, pp 201–220
41.
Zurück zum Zitat Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533CrossRef Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533CrossRef
42.
Zurück zum Zitat Watkin CJCH (1989) Learning from delayed rewards. Robot Auton Syst 15(4):233–235 Watkin CJCH (1989) Learning from delayed rewards. Robot Auton Syst 15(4):233–235
43.
Zurück zum Zitat Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of AAAI, pp 2094–2100 Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of AAAI, pp 2094–2100
44.
Zurück zum Zitat Van Hasselt H (2010) Double Q-learning. In: Proceedings of AAAI, pp 2613–2621 Van Hasselt H (2010) Double Q-learning. In: Proceedings of AAAI, pp 2613–2621
45.
Zurück zum Zitat Quan W, Wang K, Yan D, Zhang X (2018) Distinguishing between natural and computer-generated images using convolutional neural networks. IEEE Trans Inf Forensics Secur 13(11):2772–2787CrossRef Quan W, Wang K, Yan D, Zhang X (2018) Distinguishing between natural and computer-generated images using convolutional neural networks. IEEE Trans Inf Forensics Secur 13(11):2772–2787CrossRef
46.
Zurück zum Zitat Sun T, Wang Y, Yang J, Hu X (2017) Convolution neural networks with two pathways for image style recognition. IEEE Trans Image Process 26(9):4102–4113MathSciNetCrossRef Sun T, Wang Y, Yang J, Hu X (2017) Convolution neural networks with two pathways for image style recognition. IEEE Trans Image Process 26(9):4102–4113MathSciNetCrossRef
47.
Zurück zum Zitat Wright C (2013) Listening to music. Nelson Education, Scarborough Wright C (2013) Listening to music. Nelson Education, Scarborough
48.
Zurück zum Zitat Dhanalakshmy DM, Menon HP, Vinaya V (2017) Musical notes to MIDI conversion. In: Proceedings of international conference on advances in computing, communications and informatics, pp 799–804 Dhanalakshmy DM, Menon HP, Vinaya V (2017) Musical notes to MIDI conversion. In: Proceedings of international conference on advances in computing, communications and informatics, pp 799–804
49.
Zurück zum Zitat Colmenares G, Escalante R, Sans JF, Surós R (2011) Computational modeling of reproducing-piano rolls. Comput Music J 35(1):58–75CrossRef Colmenares G, Escalante R, Sans JF, Surós R (2011) Computational modeling of reproducing-piano rolls. Comput Music J 35(1):58–75CrossRef
50.
51.
Zurück zum Zitat Malkauthekar MD (2013) Analysis of Euclidean distance and Manhattan Distance measure in face recognition. In: Proceedings of international conference on computational intelligence and information technology, pp 503–507 Malkauthekar MD (2013) Analysis of Euclidean distance and Manhattan Distance measure in face recognition. In: Proceedings of international conference on computational intelligence and information technology, pp 503–507
52.
Zurück zum Zitat Wang L, Zhang Y, Feng J (2005) On the Euclidean distance of images. IEEE Trans PAMI 27(8):1334–1339CrossRef Wang L, Zhang Y, Feng J (2005) On the Euclidean distance of images. IEEE Trans PAMI 27(8):1334–1339CrossRef
53.
Zurück zum Zitat Greche L, Jazouli M, Es-Sbai N, Majda A, Zarghili A (2017) Comparison between Euclidean and Manhattan distance measure for facial expressions classification. In: Proceedings of international conference on wireless technologies, embedded and intelligent systems, pp 1–4 Greche L, Jazouli M, Es-Sbai N, Majda A, Zarghili A (2017) Comparison between Euclidean and Manhattan distance measure for facial expressions classification. In: Proceedings of international conference on wireless technologies, embedded and intelligent systems, pp 1–4
54.
Zurück zum Zitat Wiriyachaiporn P, Chanasit K, Suchato A, Punyabukkana P, Chuangsuwanich E (2018) Algorithmic music composition comparison. In: Proceedings of international joint conference on computer science and software engineering, pp 1–6 Wiriyachaiporn P, Chanasit K, Suchato A, Punyabukkana P, Chuangsuwanich E (2018) Algorithmic music composition comparison. In: Proceedings of international joint conference on computer science and software engineering, pp 1–6
Metadaten
Titel
A Style-Specific Music Composition Neural Network
verfasst von
Cong Jin
Yun Tie
Yong Bai
Xin Lv
Shouxun Liu
Publikationsdatum
09.06.2020
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 3/2020
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-020-10241-8

Weitere Artikel der Ausgabe 3/2020

Neural Processing Letters 3/2020 Zur Ausgabe

Neuer Inhalt