Abstract:Recently, the field of musical co-creativity has gained some momentum. In this context, our goal is twofold: to develop an intelligent listening and predictive module of chord sequences, and to propose an adapted evaluation of the associated Music Information Retrieval (MIR) tasks that are the real-time extraction of musical chord labels from a live audio stream and the prediction of a possible continuation of the extracted symbolic sequence. Indeed, this application case invites us to raise questions about th… Show more
“…Pinto et al [8] argue that current systems tend to be trained on specific genres or training data that does not always reflect the user needs; they propose a system that enables a user to perform targeted fine-tuning of a state-of-the-art deep neural network based on a very limited temporal region of annotated beat locations. Carsault et al [9] explore the estimation, prediction, and evaluation of chords in musical audio focused on the special use case of a real-time system for musical co-creativity.…”
“…Pinto et al [8] argue that current systems tend to be trained on specific genres or training data that does not always reflect the user needs; they propose a system that enables a user to perform targeted fine-tuning of a state-of-the-art deep neural network based on a very limited temporal region of annotated beat locations. Carsault et al [9] explore the estimation, prediction, and evaluation of chords in musical audio focused on the special use case of a real-time system for musical co-creativity.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.