A5092639907- Music Technology and Sound Studies
- Music and Audio Processing
- Generative Adversarial Networks and Image Synthesis
- Creativity in Education and Neuroscience
Queen Mary University of London
2024
Re ection is fundamental to creative practice.However, the plurality of ways in which people re ect when using AI Generated Content (AIGC) underexplored.This paper takes AI-based music composition as a case study explore how artist-researcher composers ected integrating AIGC into their process.The tools explored range from Markov Chains for generation Variational Auto-Encoders modifying timbre.We used novel method where our would pause and back on screenshots composing after every hour, this...
Deep learning generative AI models trained on huge datasets are capable of producing complex and high quality music. However, there few studies how Generated Content (AIGC) is actually used or appropriated in creative practice. We present two first-person accounts by musician-researchers explorations an interactive system Irish Folk The intentionally musicians from incongruous genres Punk Glitch to explore questions the model into practice it changes when outside its intended genre....
Machine Learning models are capable of generating complex music across a range genres from folk to classical music. However, current generative AI typically difficult understand and control in meaningful ways. Whilst research has started explore how explainable (XAI) might be created for music, no XAI have been studied making practice. This paper introduces an autoethnographic study the use MeasureVAE model with interpretable latent dimensions trained on Irish Findings suggest that...