A Unit Selection Methodology for Music Generation Using Deep Neural Networks
@inproceedings{Bretan2017AUS, title={A Unit Selection Methodology for Music Generation Using Deep Neural Networks}, author={M. Bretan and Gil Weinberg and Larry Heck}, booktitle={ICCC}, year={2017} }
Several methods exist for a computer to generate music based on data including Markov chains, recurrent neural networks, recombinancy, and grammars. We explore the use of unit selection and concatenation as a means of generating music using a procedure based on ranking, where, we consider a unit to be a variable length number of measures of music. We first examine whether a unit selection method, that is restricted to a finite size unit library, can be sufficient for encompassing a wide… CONTINUE READING
Supplemental Video
Figures, Tables, and Topics from this paper
34 Citations
The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
- Computer Science, Engineering
- 2018
- PDF
Rethinking Recurrent Latent Variable Model for Music Composition
- Computer Science, Engineering
- 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)
- 2018
- 4
- PDF
The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
- Computer Science
- 2019 International Workshop on Multilayer Music Representation and Processing (MMRP)
- 2019
- 12
Impromptu Accompaniment of Pop Music using Coupled Latent Variable Model with Binary Regularizer
- Computer Science
- 2019 International Joint Conference on Neural Networks (IJCNN)
- 2019
- 1
Deep learning for music generation: challenges and directions
- Computer Science
- Neural Comput. Appl.
- 2020
- 15
- Highly Influenced
Music Generation by Deep Learning - Challenges and Directions
- Computer Science, Engineering
- ArXiv
- 2017
- 19
- PDF
MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation
- Computer Science
- ISMIR
- 2017
- 203
- PDF
Deep Composer: Deep Neural Hashing And Retrieval Approach To Automatic Music Generation
- Computer Science
- 2020 IEEE International Conference on Multimedia and Expo (ICME)
- 2020
References
SHOWING 1-10 OF 40 REFERENCES
Finding temporal structure in music: blues improvisation with LSTM recurrent networks
- Computer Science
- Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing
- 2002
- 207
- PDF
Polyphonic Music Generation by Modeling Temporal Dependencies Using a RNN-DBN
- Computer Science
- ICANN
- 2014
- 29
- PDF
Unit selection in a concatenative speech synthesis system using a large speech database
- Computer Science
- 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
- 1996
- 1,310
- PDF
Generation of composed musical structures through recurrent neural networks based on chaotic inspiration
- Computer Science
- The 2011 International Joint Conference on Neural Networks
- 2011
- 16
- PDF
Developing and evaluating computational models of musical style
- Computer Science
- Artificial Intelligence for Engineering Design, Analysis and Manufacturing
- 2015
- 30
- PDF
Automatically clustering similar units for unit selection in speech synthesis
- Computer Science
- EUROSPEECH
- 1997
- 333
- PDF
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Computer Science, Mathematics
- ICML
- 2012
- 530
- PDF