AI-Based Affective Music Generation Systems: A Review of Methods, and Challenges

Dash, Adyasha; Agres, Kat

doi:10.48550/arxiv.2301.06890

Cited by 2 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝑛 𝑚 (10) Take the greatest high-frequency coefficient out of the 𝐺 𝜔 (𝑚, 𝑛) values that correspond to the two photos that will be combined to represent the spliced scene. The machine used for this experiment has a Windows 7 operating system, an Intel Core i3 processor with a primary clock of 2.26GHz, and 4GB of memory.…”

Section: 𝐺 𝜔 (𝑚 𝑛) = − ∑ ∑ 𝐿 𝑚 (𝑚 𝑛)𝑙𝑛[𝐿 𝑚 (𝑚 𝑛)]mentioning

confidence: 99%

See 1 more Smart Citation

Animation Vr Scene Stitching Modeling Based on Genetic Algorithm

Chen

2024

IJCAI

View full text Add to dashboard Cite

The process of seamlessly combining many Virtual reality (VR) scenes to create a continuous and engaging VR experience is known as VR scene stitching. It comprises stitching together several scenes or locations to provide smooth transitions between them without any noticeable seams or interruptions. Each VR scene is carefully designed and created, focusing on certain areas, objects, or events within the virtual environment. To enhance the expertise based on the already employed animation VRSSM (VR scene stitching modeling), more research is conducted on the animation VRSSM in conjunction with Genetic Algorithms (GA). The approach uses a wavelet transform (WT) to recover the scene's low-and high-frequency components for use in animation. Splicing criteria for the high-frequency coefficients are determined by comparing and filtering the convolution outcomes from 2 GA pattern operators. The GA sharpness assessment function and the 8 neighborhood local variance are used to determine the splice procedure for the low frequency coefficients; to produce the mosaic modeling of the stitching scene; the inverse WT is utilized. The subjective and objective assessment approaches are used together to examine the experimental outcomes. The data demonstrate that the GA achieves a higher quality splice (0.38) than the traditional splicing modeling. Rich edge information and great scene clarity are benefits of animation scene splicing modeling. The method suggested in this study outperforms the standard algorithm in terms of both qualitative and quantitative evaluation, and its implementation yields a potent synergistic impact on VR scene stitching.Povzetek: Raziskava izboljšuje združevanje VR scen z uporabo genetskih algoritmov in valčne transformacije, kar omogoča kakovostnejše in bolj jasne prehode med scenami.

show abstract

Section: 𝐺 𝜔 (𝑚 𝑛) = − ∑ ∑ 𝐿 𝑚 (𝑚 𝑛)𝑙𝑛[𝐿 𝑚 (𝑚 𝑛)]mentioning

confidence: 99%

“…Every chromosome stands for a possible answer to the issue at hand. After that, the population changes throughout some generations [10]. The procedure begins with the generation of a population of arbitrary people (chromosomes).…”

Section: Introductionmentioning

confidence: 99%

Animation Vr Scene Stitching Modeling Based on Genetic Algorithm

Chen

2024

IJCAI

View full text Add to dashboard Cite

show abstract

“…A review of automatic music generation is out of the scope of this article (for a review and summary of the state-of-the-art, see Herremans et al, 2017 ; Carnovalini and Rodà, 2020 ; Dash and Agres, 2023 ), however we will briefly summarize the main approaches to automatic music generation. Previous approaches to developing music generation systems largely fall into two categories: learning-based methods, and rule-based methods.…”

Section: Introductionmentioning

confidence: 99%

AffectMachine-Classical: a novel system for generating affective classical music

2023

Self Cite

View full text Add to dashboard Cite

This work introduces a new music generation system, called AffectMachine-Classical, that is capable of generating affective Classic music in real-time. AffectMachine was designed to be incorporated into biofeedback systems (such as brain-computer-interfaces) to help users become aware of, and ultimately mediate, their own dynamic affective states. That is, this system was developed for music-based MedTech to support real-time emotion self-regulation in users. We provide an overview of the rule-based, probabilistic system architecture, describing the main aspects of the system and how they are novel. We then present the results of a listener study that was conducted to validate the ability of the system to reliably convey target emotions to listeners. The findings indicate that AffectMachine-Classical is very effective in communicating various levels of Arousal (R2 = 0.96) to listeners, and is also quite convincing in terms of Valence (R2 = 0.90). Future work will embed AffectMachine-Classical into biofeedback systems, to leverage the efficacy of the affective music for emotional wellbeing in listeners.

show abstract

AI-Based Affective Music Generation Systems: A Review of Methods, and Challenges

Cited by 2 publications

References 46 publications

Animation Vr Scene Stitching Modeling Based on Genetic Algorithm

Animation Vr Scene Stitching Modeling Based on Genetic Algorithm

AffectMachine-Classical: a novel system for generating affective classical music

Contact Info

Product

Resources

About