Exploring XAI for the Arts: Explaining Latent Space in Generative Music
Preprint
Abstract
Explainable AI has the potential to support more interactive and fluid co-creative AI systems which can creatively collaborate with people. To do this, creative AI models need to be amenable to debugging by offering eXplainable AI (XAI) features which are inspectable, understandable, and modifiable. However, currently there is very little XAI for the arts. In this work, we demonstrate how a latent variable model for music generation can be made more explainable; specifically we extend MeasureVAE which generates measures of music. We increase the explainability of the model by: i) using latent space regularisation to force some specific dimensions of the latent space to map to meaningful musical attributes, ii) providing a user interface feedback loop to allow people to adjust dimensions of the latent space and observe the results of these changes in real-time, iii) providing a visualisation of the musical attributes in the latent space to help people understand and predict the effect of changes to latent space dimensions. We suggest that in doing so we bridge the gap between the latent space and the generated musical outcomes in a meaningful way which makes the model and its outputs more explainable and more debuggable.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Concept whitening for interpretable image recognitionNature Machine Intelligence, 2020
- Deep Learning Techniques for Music Generation2020
- Look who’s talking now: Implications of AV’s explanations on driver’s trust, AV preference, anxiety and mental workloadTransportation Research Part C: Emerging Technologies, 2019
- Machine learning research that matters for music creation: A case studyJournal of New Music Research, 2018
- XiaoIce Band2018
- GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures2017
- A Functional Taxonomy of Music Generation SystemsACM Computing Surveys, 2017
- Third-wave HCI, 10 years later---participation and sharingInteractions, 2015
- How can computers be partners in the creative process: Classification and commentary on the Special IssueInternational Journal of Human-Computer Studies, 2005
- Scenarios and the HCI-SE design problemInteracting with Computers, 2002