Some Reflections on the Potential and Limitations of Deep Learning for Automated Music Generation
- 1 September 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 27-31
Abstract
Deep Learning and Artificial Intelligence are slowly revolutionizing many fields of applications, having the potential to replace humans in a variety of tasks and jobs. Nevertheless, creativity has always been considered something inherently human: recent research shows that, however, this may not always be the case. From this standpoint, this paper focuses on music and on the recent advancements in deep learning applied to the generation of musical content. We argue that, while those models are able to produce results that could actually be considered music, the role of the human musician still remains preponderant in the production of a musical piece. We here reflect on such limitations, directing our efforts to imagining new tools and instruments that may allow to experience new forms of interaction while supporting novel processes of creativity and music production.Keywords
This publication has 10 references indexed in Scilit:
- Attitudes of Crohn’s Disease Patients: Infodemiology Case Study and Sentiment Analysis of Facebook and Twitter PostsJMIR Public Health and Surveillance, 2017
- Analysis of ECN/RED and SAP-LAW with simultaneous TCP and UDP trafficComputer Networks, 2016
- Unleashing the true potential of social networks: confirming infliximab medical trials through Facebook postsNetwork Modeling Analysis in Health Informatics and Bioinformatics, 2016
- Show and tell: A neural image caption generator2015
- Road crossing recognition through smartphone's accelerometer2011
- MDTN: Mobile Delay/Disruption Tolerant Network2011
- Markov constraints: steerable generation of Markov sequencesConstraints, 2010
- First Responders' Crystal Ball: How to Scry the Emergency from a Remote Vehicle2007 IEEE International Performance, Computing, and Communications Conference, 2007
- Finding temporal structure in music: blues improvisation with LSTM recurrent networks2003
- Long Short-Term MemoryNeural Computation, 1997