The pop song generator: designing an online course to teach collaborative, creative AI
Abstract: This article describes and evaluates a new online AI-creativity course. The course is based around three near-state-of-the-art AI models combined into a pop song generating system. A fine-tuned GPT-2 model writes lyrics, Music-VAE composes musical scores and instrumentation and Diffsinger synthesises a singing voice. We explain the decisions made in designing the course which is based on Piagetian, constructivist 'learning-by-doing'. We present details of the five-week course design with learning objectives, technical concepts, and creative and technical activities. We explain how we overcame technical challenges to build a complete pop song generator system, consisting of Python scripts, pre-trained models, and Javascript code that runs in a dockerised Linux container via a web-based IDE. A quantitative analysis of student activity provides evidence on engagement and a benchmark for future improvements. A qualitative analysis of a workshop with experts validated the overall course design, it suggested the need for a stronger creative brief and ethical and legal content.
- Teaching computational creativity. In International Conference on Computational Creativity. ICCC, 2017.
- Reflecting on reflexive thematic analysis. Qualitative Research in Sport, Exercise and Health, 11(4):589–597, 2019.
- Lisa G Catterall. A brief history of stem and steam from an inadvertent insider. The STEAM Journal, 3(1):5, 2017.
- What makes it hard to teach software engineering to end users? In 2013 26th International Conference on Software Engineering Education and Training (CSEET), pages 324–328, 2013.
- Stakeholder groups in computational creativity research and practice. Computational creativity research: towards creative machines, pages 3–36, 2015.
- Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341, 2020.
- Rebecca Fiebrink. Machine learning education for artists, musicians, and other creative practitioners. ACM Transactions on Computing Education (TOCE), 19(4):1–32, 2019.
- Image co-creation by non-programmers and generative adversarial networks. In Joint Proceedings of the ACM IUI 2021 Workshops, 2021.
- Danah Henriksen. Full steam ahead: Creativity in excellent stem teaching practices. The STEAM journal, 1(2):15, 2014.
- Drivers of quality in online learning, 2020.
- Giving voice and making sense in interpretative phenomenological analysis. Qualitative Research in Psychology, 3(2):102–120, 2006.
- Keon Lee. Diffsinger. https://github.com/keonlee9420/DiffSinger, 2021.
- Hye-Kyung Lee. Rethinking creativity: creative industries, ai and everyday creativity. Media, Culture & Society, 44(3):601–612, 2022.
- Jinglin et al. Liu. Diffsinger: Diffusion acoustic model for singing voice synthesis. arXiv e-prints, pages arXiv–2105, 2021.
- Earsketch: A steam-based approach for underrepresented populations in high school computer science education. ACM Transactions on Computing Education (TOCE), 16(4):1–25, 2016.
- A systematic mapping study on practical approaches to teaching software engineering. In 2014 IEEE Frontiers in Education Conference (FIE) Proceedings, pages 1–8, 2014.
- Teaching machine learning in school: A systematic mapping of the state of the art. Informatics in Education, 19(2):283–321, 2020.
- Seymour Papert. Mindstorms: children, computers, and powerful ideas, 1980.
- Jean Piaget. Psychology and epistemology: towards a theory of knowledge. Penguin, 1978.
- AÂ Roberts. Musicvae: Creating a palette for musical scores with machine learning, march 2018, 2018.
- Artificial intelligence: a modern approach, global edition 4th. Pearson, 2021.
- Pedagogies of machine learning in k-12 context. In 2020 IEEE Frontiers in Education Conference (FIE), pages 1–8. IEEE, 2020.
- Envisioning ai for k-12: What should every child know about ai? In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 9795–9799, 2019.
- Conceptualizing authenticity in engineering education: A systematic literature review. In 2012 ASEE Annual Conference & Exposition, pages 25–340, 2012.
- Promoting intentions to persist in computing: an examination of six years of the earsketch program. Computer Science Education, 30(4):394–419, 2020.
- Carla Willig. Grounded Theory, pages 34–51. McGraw-Hill Education, 2008.
- Thomas et al. Wolf. Huggingface’s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771, 2019.
- Modelling adult learners’ online engagement behaviour: proxy measures and its application. Journal of Computers in Education, 5(4):463–479, 2018.
- Steam works: Student coders experiment more and experimenters gain higher grades. In 2017 IEEE Global Engineering Education Conference (EDUCON), pages 359–366. IEEE, 2017.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
