Markov Chains for Computer Music Generation

Shapiro, Ilana; Huber, M. E.

doi:10.5642/jhummath.202102.08

Cited by 12 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, some sounds have special treatment. The first lead has an LFO to modify its amplitude, and the second lead has another LFO to modify its frequency [10][11][12]. For drum sound, a low-pass filter after a white noise generator is used to simulate the kick sound, and a high-pass filter is used to simulate the hi-hat sound.…”

Section: Methodsmentioning

confidence: 99%

Synthetic Music Random Generation Based on Nyquist

Li,

Ma,

Zou

2024

HSET

View full text Add to dashboard Cite

The idea of composing music based on programs has a long history, from some pioneers who first tried to fulfill this idea, to now, the variety of software and workshops that allow people to generate music in different approaches. On this basis, this study will briefly discuss the main idea and some methods used to compose the music in this paper. We aimed to randomly generate a piece of music using only Nyquist. Thus, each time when listen to this, there is a slight difference. With this in mind, this paper has used two ways: the first one is to use several functions in Nyquist, which would randomly choose numbers in a given list or range. The second way is a method based on the functions mentioned earlier, called the random walk, which lets the program stochastically choose one item in a given list of a range of numbers every time to add or subtract to the origin number given by programmers. By using these two techniques, one can generate random sounds and random rhythmic patterns, and when we put these sounds and patterns into scores to generate various melodies, we can stochastically increase or decrease the overall pitch of that score. Finally, the scores are combined to create the whole piece of music. Although there are limitations, this study has provided some methods that can be useful for generating stochastic music.

show abstract

Section: Methodsmentioning

confidence: 99%

Synthetic Music Random Generation Based on Nyquist

Li,

Ma,

Zou

2024

HSET

View full text Add to dashboard Cite

show abstract

“…Outside of the industry, automatic music generation for games as a research topic has seen more interest in recent years, often focusing on rules-based approaches or less computationally taxing approaches such as Markov chains to decrease latency and computational costs in real-time [19], [51], which in turn increases performance expectancy [61]. However, there is a disconnect between industry and academia, so while research has been tackling game-specific use cases such as transition generation [15], generating music that adapts to gameplay [29], using gaussian mixtures to control melodic shape in generative music [72] or generating music to match nonplayer character relationships [63], procedural music systems that generate new material go largely ignored in industry.…”

Section: Procedural Music Generationmentioning

confidence: 99%

Considerations and Concerns of Professional Game Composers Regarding Artificially Intelligent Music Technology

Worrall,

Collins

2024

IEEE Trans. Games

View full text Add to dashboard Cite

Artificially intelligent music technology (AIMT) is a promising field with great potential for creating innovation in music. However, the considerations and concerns surrounding AIgenerated music from the perspective of professional video game composers have yet to be fully explored. In this study, 11 professional video game composers were interviewed to determine how they feel about AIMT and how this informs future research and tool design within the games industry. The interviews were analyzed using a reflexive thematic analysis (RTA) to identify key themes. The study found that while composers recognize the benefits of music AI, they have complex concerns beyond the obvious concerns for AI infringing on their agency and creativity. There is an inherent clash between the creative ego and music AI, which can make it difficult for composers to embrace this technology. Furthermore, a lack of standard technical knowledge, support, understanding, and trust of music AI is impeding tool use within the industry. These findings have implications for music AI researchers and industry practitioners. By better understanding the concerns and considerations of professional creatives, researchers can design and communicate their tools more effectively to music professionals. Moreover, this study lays the foundation for empirical research into the relationship between professional creatives and emerging AI technology -a topic that is under-emphasised in current research.

show abstract

“…Given a set of rules, it is crucial to devise a method to compute them to generate sequences. There are many ways of doing this with 'classical' computing methods, which will not be discussed here [3,17,49]. Rather, we are interested in exploring ways of doing it quantumly.…”

Section: Composing With Transition Rulesmentioning

confidence: 99%

Teaching Qubits to Sing: Mission Impossible?

Miranda¹,

Siegelwax²

2022

Preprint

View full text Add to dashboard Cite

This paper introduces QuSing, a system that learns to sing new tunes by listening to examples. QuSing 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 system's creative potential. Accompanying materials are available in an Appendix. Audio recordings of the musical examples and programming code are available: https://github.com/iccmr-quantum/QuSing.

show abstract

Markov Chains for Computer Music Generation

Cited by 12 publications

References 0 publications

Synthetic Music Random Generation Based on Nyquist

Synthetic Music Random Generation Based on Nyquist

Considerations and Concerns of Professional Game Composers Regarding Artificially Intelligent Music Technology

Teaching Qubits to Sing: Mission Impossible?

Contact Info

Product

Resources

About