Abstract
The generation of musical material in a given style has been the subject of many studies with the increased sophistication of artificial intelligence models of musical style. In this paper we address a question of primary importance for artificial intelligence and music psychology: can such systems generate music that users indeed consider as corresponding to their own style? We address this question through an experiment involving both performance and recognition tasks with musically naïve school-age children. We asked 56 children to perform a free-form improvisation from which two kinds of music excerpt were created. One was a mere recording of original performances. The other was created by a software program designed to simulate the participants' style, based on their original performances. Two hours after the performance task, the children completed the recognition task in two conditions, one with the original excerpts and one with machine-generated music. Results indicate that the success rate is practically equivalent in two conditions: children tended to make correct attribution of the excerpts to themselves or to others, whether the music was human-produced or machine-generated (mean accuracy = 0.75 and = 0.71, respectively). We discuss this equivalence in accuracy for machine-generated and human produced music in the light of the literature on memory effects and action identity which addresses the recognition of one's own production.
Highlights
Recent progress in artificial intelligence and statistical inference make it possible to generate artificially musical material in a given musical style
Do subjects consider as their own style music that has been machine-generated by recombining their original material so as to maintain stylistic consistency? Do the machine-generated excerpts sound like “my music?” We address this research question by comparing the accuracy of style attribution of machine-generated musical excerpts with the accuracy of selfrecognition task in human-produced excerpts
The original data set a1 suggests that there is no significant difference between the accuracy of self-recognition for the melodies played by participants and the accuracy of style attribution for the machine-generated pieces (M = 0.75, M = 0.71, respectively, against the chance level of 0.5)
Summary
Recent progress in artificial intelligence and statistical inference make it possible to generate artificially musical material in a given musical style. From the viewpoint of artificial intelligence, a style is essentially a statistical object, characterized by the statistics of occurrence of the various elements making up a musical production (e.g., notes), as well as the statistics of their interrelationships. The increasing sophistication of style-based music generation systems raises novel questions at the frontier of artificial intelligence and the psychology of music perception. An important question is to what extent the human player considers the musical result of this generation as reproducing his or her own style. Musical style simulation has been the subject of many studies in artificial intelligence resulting in a steady stream of software attempting to imitate musical style (see e.g., Thomas et al, 2013).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
