Abstract
Jazz improvisation on a given lead sheet with chords is an interesting scenario for studying the behaviour of artificial agents when they collaborate with humans. Specifically in jazz improvisation, the role of the accompanist is crucial for reflecting the harmonic and metric characteristics of a jazz standard, while identifying in real-time the intentions of the soloist and adapt the accompanying performance parameters accordingly. This paper presents a study on a basic implementation of an artificial jazz accompanist, which provides accompanying chord voicings to a human soloist that is conditioned by the soloing input and the harmonic and metric information provided in a lead sheet chart. The model of the artificial agent includes a separate model for predicting the intentions of the human soloist, towards providing proper accompaniment to the human performer in real-time. Simple implementations of Recurrent Neural Networks are employed both for modeling the predictions of the artificial agent and for modeling the expectations of human intention. A publicly available dataset is modified with a probabilistic refinement process for including all the necessary information for the task at hand and test-case compositions on two jazz standards show the ability of the system to comply with the harmonic constraints within the chart. Furthermore, the system is indicated to be able to provide varying output with different soloing conditions, while there is no significant sacrifice of “musicality” in generated music, as shown in subjective evaluations. Some important limitations that need to be addressed for obtaining more informative results on the potential of the examined approach are also discussed.
Highlights
The use of automatic systems for generating music is a captivating vision and a multidisciplinary research problem studied for decades
The diversity of music generative systems relies on their different objectives and the musical content that they produce, such as chord progressions, melody generation, accompaniment arrangements and counterpoints (Briot et al, 2019)
The harmony alternation model receives a given chord progression in order to transform it to a different one that fits better with a specified music style based on Hidden Markov Models (HMMs)
Summary
The use of automatic systems for generating music is a captivating vision and a multidisciplinary research problem studied for decades. Wang and Xia (2018) developed a framework for generating both lead melody and piano accompaniment arrangements of pop music. The feature extraction stage is responsible to compute symbolic-domain harmonic features from the given lead sheet in order to condition the generation of the arrangement. They consider a chord progression as input and propose three phases for generating a structured melody with layered piano accompaniments. The melody generation model generates the lead melody and the layered accompaniment voices through seasonal ARMA (Autoregressive Moving Average) processes. The final phase implements the melody integration model which is responsible for integrating the melody voices together as the final piano accompaniment
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.
