Calliope: Generating Symbolic Multi-Track Music on the Web

International Journal of Innovative Technology and Exploring Engineering, 2020

Humans have been entertained by music for millennia. For ages it has been treated as an art form which requires a lot of imagination, creativity and accumulation of feelings and emotions. Recent trends in the field of Artificial Intelligence have been getting traction and Researchers have been developing and generating rudimentary forms of music through the use of AI. Our goal is to generate novel music, which will be non-repetitive and enjoyable. We aim to utilize a couple of Machine Learning models for the same. Given a seed bar of music, our first Discriminatory network consisting of Support Vector Machines and Neural Nets will choose a note/chord to direct the next bar. Based on this chord or note another network, a Generative Net consisting of Generative Pretrained Transformers(GPT2) and LSTMs will generate the entire bar of music. Our two fold method is novel and our aim is to make the generation method as similar to music composition in reality as possible. This in turn resul...

International Journal on Artificial Intelligence Tools, 2005

Nobody would deny that music may evoke deep and profound emotions. In this paper, we present a perceptual music composition system that aims at the controlled manipulation of a user's emotional state. In contrast to traditional composing techniques, the single components of a composition, such as melody, harmony, rhythm and instrumentation, are selected and combined in a user-specific manner without requiring the user to continuously provide comments on the music employing input devices, such as keyboard or mouse.

IEEE Access

Music generation using deep learning has received considerable attention in recent years. Researchers have developed various generative models capable of imitating musical conventions, comprehending the musical corpora, and generating new samples based on the learning outcome. Although the samples generated by these models are persuasive, they often lack musical structure and creativity. For instance, a vanilla end-to-end approach, which deals with all levels of music representation at once, does not offer human-level control and interaction during the learning process, leading to constrained results. Indeed, music creation is a recurrent process that follows some principles by a musician, where various musical features are reused or adapted. On the other hand, a musical piece adheres to a musical style, breaking down into precise concepts of timbre style, performance style, composition style, and the coherency between these aspects. Here, we study and analyze the current advances in music generation using deep learning models through different criteria. We discuss the shortcomings and limitations of these models regarding interactivity and adaptability. Finally, we draw the potential future research direction addressing multi-agent systems and reinforcement learning algorithms to alleviate these shortcomings and limitations.

Creativity and Cognition

Calliope is a web application for co-creative multi-track music composition (MMM) in the symbolic domain. It is built to facilitate the use of multi-track music machine (MMM). The user can upload Musical Instrument Digital Interface (MIDI) files, visualize * All authors contributed equally to this research.

Artificial Intelligence in Music, Sound, Art and Design

We present a novel music generation framework for music infilling, with a user friendly interface. Infilling refers to the task of generating musical sections given the surrounding multi-track music. The proposed transformer-based framework is extensible for new control tokens as the added music control tokens such as tonal tension per bar and track polyphony level in this work. We explore the effects of including several musically meaningful control tokens, and evaluate the results using objective metrics related to pitch and rhythm. Our results demonstrate that adding additional control tokens helps to generate music with stronger stylistic similarities to the original music. It also provides the user with more control to change properties like the music texture and tonal tension in each bar compared to previous research which only provided control for track density. We present the model in a Google Colab notebook to enable interactive generation.

arXiv (Cornell University), 2020

We propose the Multi-Track Music Machine (MMM), a generative system based on the Transformer architecture that is capable of generating multi-track music. In contrast to previous work, which represents musical material as a single time-ordered sequence, where the musical events corresponding to different tracks are interleaved, we create a time-ordered sequence of musical events for each track and concatenate several tracks into a single sequence. This takes advantage of the Transformer's attention-mechanism, which can adeptly handle longterm dependencies. We explore how various representations can offer the user a high degree of control at generation time, providing an interactive demo that accommodates track-level and bar-level inpainting, and offers control over track instrumentation and note density.

2007

iv ACKNOWLEDGEMENTS I would like to thank the members of my committee for their support, patience and the many ways in which they have inspired me. I would also like to thank: Lance Putnam, for both the sharing of and support for his Synz audio library, and synthesis programming in general, Wesley Smith for inspiration and support both creatively and technically regarding 3-D graphics, and for the OpenGL bindings to Lua, Norman, and the author) for resources in the in the windowing/GUI implementation, Stephen Pope and Xavier Amatriain for instruction in software synthesis and event scheduling, My friends, family and loved ones for endless support, encouragement and patience. The rich new terrains offered by computer music invite the exploration of new techniques to compose within them. The computational nature of the medium has suggested algorithmic approaches to composition in the form of generative musical structure at the note level and above, and audio signal processing at the l...

2003

This paper presents a design of support system for musical composition based on Simulated Breeding. In our system named SBEAT3, each individual in the population is a short musical section of sixteen beats including 23 parts, thirteen solos, two chords and eight percussions.The melody and rhythm are generated by a type of recursive algorithm from genetic information. By selecting favorite piece among scores displayed on the screen, the user listens to the sounds and decides which should be theparents to reproduce the offspring in the next generation. The genetic codes of children are generated through mutation and crossover. Iterating this process, the user obtains better pieces gradually. Embedding some domain specific functions, such as changing tempo and selecting tones, we can build a useful tool to make it easier for a beginner to compose his/her favorite musical pieces.

Journal of Creative Music Systems

The International conference on AI Music Creativity (AIMC, https://aimusiccreativity.org/) is the merger of the international workshop on Musical Metacreation MUME (https://musicalmetacreation.org/) and the conference series on Computer Simulation of Music Creativity (CSMC, https://csmc2018.wordpress.com/). This special issue gathers selected papers from the first edition of the conference along with paper versions of two of its keynotes.This special issue contains six papers that apply novel approaches to the generation and classification of music. Covering several generative musical tasks such as composition, rhythm generation, orchestration, as well as some machine listening task of tempo and genre recognition, these selected papers present state of the art techniques in Music AI. The issue opens up with an ode on computer Musicking, by keynote speaker Alice Eldridge, and Johan Sundberg's use of analysis-by-synthesis for musical applications.

2000

This paper describes Roboser (http://www.roboser.com), an autonomous interactive music composition system. The core of the system comprises two components: a program for simulating large-scale neural networks, and an algorithmic composition system. Both components operate in real-time. Data from e.g. cameras, microphones and pressure sensors enter the simulated neural system, which is also used to actively control motor devices such as pantilt cameras and robots. The neural system relays data representing its current operational state on to the algorithmic composition system. The composition system in turn generates musical expressions of these neural states within an a priori stylistic framework. The result is a real-time system controlled by a brain-like structure that behaves and interacts within a given environment and expresses its internal states through music.