Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

WORLD SCIENTIFIC eBooks

Music AI with Quantum Reservoir Computing

Eduardo Reck Miranda, Hari Vignesh Shaji

Published Jan 1, 2025• 0 citations
Publisher

Abstract

Artificial intelligence (AI) has recently gained much interest in inspiring and facilitating artists to expand their creative possibilities. Exploiting the physical properties of a quantum system, this chapter proposes Quantum Reservoir Computing (QRC) to build music AI systems. We developed a QRC-based proof-of-concept system that learns music sequencing rules from examples in a given corpus and uses these rules to generate new music. The QRC approach introduced here has demonstrable advantages over the standard deep-learning approaches normally adopted for music AI, one of which is the considerable reduction in the required number of trainable parameters. A proof-of-concept system is demonstrated.

DOI
10.1142/9789819800186_0009

Related papers

A quantum reservoir computing approach to computer-aided music composition

Eduardo Reck Miranda, Hari Vignesh Shaji

This paper presents an approach to developing computer-aided music composition (CAMC) systems with quantum computing. CAMC systems are aimed at supporting musicians in creating music rather than generating complete pieces of music autonomously. For instance, they may generate ideas or prompts to be further developed during the creative process. We developed a CAMC system using a machine learning method called Quantum Reservoir Computing (QRC) that learns to create tunes in the style of given examples. The system proved to run satisfactorily on the Noisy Intermediate-Scale Quantum (NISQ) machines available today. It does not require large amounts of qubits to outperform equivalent classical Deep Learning methods. Furthermore, it can serve the purposes of a CAMC system without the need for big data for training. This paper provides a general introduction to reservoir computing fundamentals and explains how quantum mechanics can harness its performance. Then, it walks the reader through the development of our system and presents demonstrations. A comparative experiment against a classic Recurrent Neural Network (RNN) model is also discussed.

Academia quantum.•May 26, 2025•3 citations

A Quantum Natural Language Processing Approach to Musical Intelligence

Miranda, ER, Yeung, R, Pearson, A +2 more

There has been tremendous progress in Artificial Intelligence (AI) for music, in particular for musical composition and access to large databases for commercialisation through the Internet.We are interested in further advancing this field, focusing on composition.In contrast to current 'blackbox' AI methods, we are championing an interpretable compositional outlook on generative music systems.In particular, we are importing methods from the Distributional Compositional Categorical (DisCoCat) modelling framework for Natural Language Processing (NLP), motivated by musical grammars.Quantum computing is a nascent technology, which is very likely to impact the music industry in time to come.Thus, we are pioneering a Quantum Natural Language Processing (QNLP) approach to develop a new generation of intelligent musical systems.This work follows from previous experimental implementations of DisCoCat linguistic models on quantum hardware.In this chapter, we present Quanthoven, the first proof-of-concept ever built, which (a) demonstrates that it is possible to program a quantum computer to learn to classify music that conveys different meanings and (b) illustrates how such a capability might be leveraged to develop a system to compose meaningful pieces of music.After a discussion about our current understanding of music as a communication medium and its relationship to natural language, the chapter focuses on the techniques developed to (a) encode musical compositions as quantum circuits, and (b) design a quantum classifier.The chapter ends with demonstrations of compositions created with the system.

arXiv:2111.06741•Nov 10, 2021•8 citations

The application of quantum computing in music composition

Johee Lee, Weijia Yang

Quantum computing and artificial intelligence, two prominent topics in science and technology, are rapidly advancing and extending their influence into numerous fields, including music. Quantum computer music, which merges the strengths of quantum computing and deep learning, heralds a new era in the integration of music creation with cutting-edge technology. The interactive quantum music composition “Spinnings—Q1 Synth Trio”, created by Brazilian composer Miranda during the QuTune project at the Interdisciplinary Centre for Computer Music Research (ICCMR), in collaboration with the University of Oxford, stands as a notable example of quantum computer music. This study adopts a case study approach to thoroughly investigate the technical creative process behind this work, covering elements such as quantum computing, quantum properties, qubits, quantum gates, and quantum circuits, gradually unveiling the mathematical logic behind quantum algorithmic composition. The results of this study indicate that quantum algorithmic composition, as an emerging approach to music creation, not only generates unique music through the characteristics of quantum computing but also offers new possibilities for the integration of music, art, and technology. By applying quantum bits, quantum gates, and quantum circuits, this research demonstrates how quantum computing can provide new theoretical foundations and practical methods for music composition. Furthermore, the study discusses how to optimize the interactive creative experience in quantum music works and how to enhance the understanding and appreciation of quantum music among a broader audience of musicians and listeners. With the continuous advancement of quantum computing technology, quantum music is poised to contribute a distinctive dimension to the global flourishing of musical culture. This research offers fresh perspectives and ideas for the development of this field.

Online Journal of Music Sciences•Dec 31, 2024•1 citation

Quantum Reservoir Computing: Recent Advances and Future Directions

Shehbaz Tariq, Muhammad Talha, Arshid Ali +2 more

Quantum reservoir computing (QRC) uses the dynamics of a fixed or weakly tuned quantum system to transform temporal and sequential inputs into measured features, while training is typically confined to a classical readout. This separation reduces reliance on repeated quantum parameter updates and avoids the barren plateaus associated with variational circuit training. Its computational power is often attributed to the exponentially large Hilbert space of the quantum system. However, the memory, nonlinearity, and expressivity that determine what a reservoir can actually compute depend jointly on the input encoding, quantum evolution, observables, measurement, and readout, not on Hilbert space dimension alone. On hardware, these capabilities are further constrained by finite sampling, hardware noise, measurement backaction, and the cost of estimating observables, so a large state space alone does not guarantee useful computation. In this survey, we develop a common system model that connects these components and use it to organize QRC foundations, computational properties, reservoir architectures, operating protocols, and physical implementations. We examine spin, photonic, superconducting, bosonic, neutral atom, and other analog platforms, together with applications, software and high performance computing support, benchmarking, and reproducibility. The analysis distinguishes hardware demonstrations from simulations and identifies the assumptions and resources that govern comparisons across implementations. Current results do not establish a broad quantum advantage over well matched classical reservoirs. We therefore specify the resource accounting, benchmark standards, and theoretical criteria needed to evaluate claims of quantum advantage.

quant-pharXiv:2607.18552•Jul 22, 2026•5 citations

Teaching Qubits to Sing: Mission Impossible?

Eduardo Reck Miranda, Brian N. Siegelwax

This paper introduces a system that learns to sing new tunes by listening to examples. It extracts sequencing rules from input music and uses these rules to generate new tunes, which are sung by a vocal synthesiser. We developed a method to represent rules for musical composition as quantum circuits. We claim that such musical rules are quantum native: they are naturally encodable in the amplitudes of quantum states. To evaluate a rule to generate a subsequent event, the system builds the respective quantum circuit dynamically and measures it. After a brief discussion about the vocal synthesis methods that we have been experimenting with, the paper introduces our novel generative music method through a practical example. The paper shows some experiments and concludes with a discussion about harnessing the creative potential of the system.

arXiv:2207.08225•Jul 17, 2022•3 citations

The advent of quantum computer music: mapping the field

Eduardo Reck Miranda

Quantum computing technology is developing at a fast pace. The impact of quantum computing on the music industry is inevitable. This paper maps the emerging field of quantum computer music. Quantum computer music investigates, and develops applications and methods to process music using quantum computing technology. The paper begins by contextualising the field. Then, it discusses significant examples of various approaches developed to date to leverage quantum computing to learn, process and generate music. The methods discussed range from rendering music using data from physical quantum mechanical systems and quantum mechanical simulations to computational quantum algorithms to generate music, including quantum AI. The ambition to develop techniques to encode audio quantumly for making sound synthesisers and audio signal processing systems is also discussed.

Reports on Progress in Physics•Jul 12, 2024•5 citations
Artificial intelligence (AI) has recently gained much interest in inspiring and facilitating artists to expand their creative possibilities. Exploiting the physical properties of a quantum system, this chapter proposes Quantum Reservoir Computing (QRC) to build music AI systems. We developed a QRC-based proof-of-concept system that learns music sequencing rules from examples in a given corpus and uses these rules to generate new music. The QRC approach introduced here has demonstrable advantages over the standard deep-learning approaches normally adopted for music AI, one of which is the considerable reduction in the required number of trainable parameters. A proof-of-concept system is demonstrated.
This paper presents an approach to developing computer-aided music composition (CAMC) systems with quantum computing. CAMC systems are aimed at supporting musicians in creating music rather than generating complete pieces of music autonomously. For instance, they may generate ideas or prompts to be further developed during the creative process. We developed a CAMC system using a machine learning method called Quantum Reservoir Computing (QRC) that learns to create tunes in the style of given examples. The system proved to run satisfactorily on the Noisy Intermediate-Scale Quantum (NISQ) machines available today. It does not require large amounts of qubits to outperform equivalent classical Deep Learning methods. Furthermore, it can serve the purposes of a CAMC system without the need for big data for training. This paper provides a general introduction to reservoir computing fundamentals and explains how quantum mechanics can harness its performance. Then, it walks the reader through the development of our system and presents demonstrations. A comparative experiment against a classic Recurrent Neural Network (RNN) model is also discussed.
There has been tremendous progress in Artificial Intelligence (AI) for music, in particular for musical composition and access to large databases for commercialisation through the Internet.We are interested in further advancing this field, focusing on composition.In contrast to current 'blackbox' AI methods, we are championing an interpretable compositional outlook on generative music systems.In particular, we are importing methods from the Distributional Compositional Categorical (DisCoCat) modelling framework for Natural Language Processing (NLP), motivated by musical grammars.Quantum computing is a nascent technology, which is very likely to impact the music industry in time to come.Thus, we are pioneering a Quantum Natural Language Processing (QNLP) approach to develop a new generation of intelligent musical systems.This work follows from previous experimental implementations of DisCoCat linguistic models on quantum hardware.In this chapter, we present Quanthoven, the first proof-of-concept ever built, which (a) demonstrates that it is possible to program a quantum computer to learn to classify music that conveys different meanings and (b) illustrates how such a capability might be leveraged to develop a system to compose meaningful pieces of music.After a discussion about our current understanding of music as a communication medium and its relationship to natural language, the chapter focuses on the techniques developed to (a) encode musical compositions as quantum circuits, and (b) design a quantum classifier.The chapter ends with demonstrations of compositions created with the system.
Quantum computing and artificial intelligence, two prominent topics in science and technology, are rapidly advancing and extending their influence into numerous fields, including music. Quantum computer music, which merges the strengths of quantum computing and deep learning, heralds a new era in the integration of music creation with cutting-edge technology. The interactive quantum music composition “Spinnings—Q1 Synth Trio”, created by Brazilian composer Miranda during the QuTune project at the Interdisciplinary Centre for Computer Music Research (ICCMR), in collaboration with the University of Oxford, stands as a notable example of quantum computer music. This study adopts a case study approach to thoroughly investigate the technical creative process behind this work, covering elements such as quantum computing, quantum properties, qubits, quantum gates, and quantum circuits, gradually unveiling the mathematical logic behind quantum algorithmic composition. The results of this study indicate that quantum algorithmic composition, as an emerging approach to music creation, not only generates unique music through the characteristics of quantum computing but also offers new possibilities for the integration of music, art, and technology. By applying quantum bits, quantum gates, and quantum circuits, this research demonstrates how quantum computing can provide new theoretical foundations and practical methods for music composition. Furthermore, the study discusses how to optimize the interactive creative experience in quantum music works and how to enhance the understanding and appreciation of quantum music among a broader audience of musicians and listeners. With the continuous advancement of quantum computing technology, quantum music is poised to contribute a distinctive dimension to the global flourishing of musical culture. This research offers fresh perspectives and ideas for the development of this field.
Quantum reservoir computing (QRC) uses the dynamics of a fixed or weakly tuned quantum system to transform temporal and sequential inputs into measured features, while training is typically confined to a classical readout. This separation reduces reliance on repeated quantum parameter updates and avoids the barren plateaus associated with variational circuit training. Its computational power is often attributed to the exponentially large Hilbert space of the quantum system. However, the memory, nonlinearity, and expressivity that determine what a reservoir can actually compute depend jointly on the input encoding, quantum evolution, observables, measurement, and readout, not on Hilbert space dimension alone. On hardware, these capabilities are further constrained by finite sampling, hardware noise, measurement backaction, and the cost of estimating observables, so a large state space alone does not guarantee useful computation. In this survey, we develop a common system model that connects these components and use it to organize QRC foundations, computational properties, reservoir architectures, operating protocols, and physical implementations. We examine spin, photonic, superconducting, bosonic, neutral atom, and other analog platforms, together with applications, software and high performance computing support, benchmarking, and reproducibility. The analysis distinguishes hardware demonstrations from simulations and identifies the assumptions and resources that govern comparisons across implementations. Current results do not establish a broad quantum advantage over well matched classical reservoirs. We therefore specify the resource accounting, benchmark standards, and theoretical criteria needed to evaluate claims of quantum advantage.
This paper introduces a system that learns to sing new tunes by listening to examples. It extracts sequencing rules from input music and uses these rules to generate new tunes, which are sung by a vocal synthesiser. We developed a method to represent rules for musical composition as quantum circuits. We claim that such musical rules are quantum native: they are naturally encodable in the amplitudes of quantum states. To evaluate a rule to generate a subsequent event, the system builds the respective quantum circuit dynamically and measures it. After a brief discussion about the vocal synthesis methods that we have been experimenting with, the paper introduces our novel generative music method through a practical example. The paper shows some experiments and concludes with a discussion about harnessing the creative potential of the system.
Quantum computing technology is developing at a fast pace. The impact of quantum computing on the music industry is inevitable. This paper maps the emerging field of quantum computer music. Quantum computer music investigates, and develops applications and methods to process music using quantum computing technology. The paper begins by contextualising the field. Then, it discusses significant examples of various approaches developed to date to leverage quantum computing to learn, process and generate music. The methods discussed range from rendering music using data from physical quantum mechanical systems and quantum mechanical simulations to computational quantum algorithms to generate music, including quantum AI. The ambition to develop techniques to encode audio quantumly for making sound synthesisers and audio signal processing systems is also discussed.