Artificial Intelligence in Music, Sound, Art and Design

This book constitutes the refereed proceedings of the 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design, EvoMUSART 2025, held as part of EvoStar 2025, in Trieste, Itlay, during April 2325, 2024.

The 28 full papers presented in this book were carefully reviewed and selected from 52 submissions.

They present a broad selection of topics and applications, including systems that create music, art, and design.

Inhalt

.- Long Talks.

.- Yin-Yang: Developing Motifs With Long-Term Structure And Controllability.

.- Foundations of LLCM: Labelled Lambek Calculus for Music Analysis.

.- Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting.

.- Cellular Au-Tonnetz: A Unified Audio-Visual MIDI Generator Using
Tonnetz, Cellular Automata, and IoT.

.- The Importance of Context in Image Generation: A Case Study for
Video Game Sprites.

.- Perceptions of AI in Animation Production.

.- Search-based Negative Prompt Optimisation for Text-to-Image Generation.

.- Exploring the Application of AIGC in Ink-Wash Animation Creation:
A Case Study of Dragon Gate.

.- AI in Music and Healthcare: A Comparative Survey.

.- Combining local search and directed mutation in evolutionary
approaches to 4-part harmony.

.- Exploiting the Temporal Order of Sound Features for Onset Detection.

.- Towards Human-Quality Drum Accompaniment Using Deep Generative
Models and Transformers.

.- An Ensemble Approach to Music Source Separation: A Comparative
Analysis of Conventional and Hierarchical Stem Separation.

.- Balancing Indeterminacy and Structure: Neural Text Generation for
Artistic Inspiration.

.- Exploring Bridges Between Algorithmic and AI-generated Art.

.- Future Sight: Fine-tuning Language Models for Dynamic Story Generation.

.- Short Talks.

.- All YIN No YANG: Geometric abstraction of oil paintings with trained
models, noise and self-reference.

.- Exploring Multi-Objective Evolution for Aesthetic & Abstract 3D Art.

.- Aesthetic biases and opacity tactics in the training of visual artificial
intelligence models.

.- Music Similarity Through Geometric Overlap.

.- Graph Neural Network vs Feature-based Folk Music Evolution Analysis.

.- Generating Virtual Landscapes and Environmental Narratives with
StyleGAN2.

.- EmotioNotes Dataset: Decoding emotions in classical music through
Concert Program Notes.

.- Towards the Automatic Evaluation of Legibility for Graphic Design
Posters.

.- Short video interestingness: a machine learning approach to determine
creative cues in audiovisual production.

.- Automated Selection and Ordering of Clip Sequences for Music Videos
based on Tonal Tension and Visual Features.

.- Evolving the Embedding Space of Diffusion Models in the Field of
Visual Arts.

.- Steering Large Text-to-Image Model for Kandinsky Synthesis through
Preference-based Prompt Optimization.