Conference: AI and Digital Innovations for Voice and Vocal Music

The Institute for Advanced Studies in the Humanities (IASH) at the University of Edinburgh is thrilled to announce an international and interdisciplinary symposium on the intersection of music and AI, with a particular focus on the performance of voice, song and the composition of vocal music highlighting AI-based singing or voice processing tools. Building on the AI & chamber music conference organised by IASH Fellow Dr Alexandra Huang-Kokina with the University of London earlier this year, this one-day symposium aims to extend the initial critical conversation. It will provide a forum for peer feedback, networking and community building for scholars, creative practitioners and postgraduate research students working at the fascinating crossroads of music, creativity, and AI studies.

Call-for-papers information here (Note: CFP deadline closed, programme announcement coming soon. Limited spots for paper presentations are available. If you'd still like to present, please contact us asap).

At the heart of this symposium on vocal music is the promotion of diversity in vocal representations via AI, featuring critical discussions centred around how AI’s creative intelligence challenges and redefines conventional vocal types defined by gender, ethnic-cultural, linguistic and neural norms. The symposium celebrates underrepresented voices in two notable ways: by using AI to amplify a diverse range of ‘singing voices’ during the symposium’s signature opera concerts at the Reid Concert Hall, and by inviting presenters from diverse backgrounds to contribute ‘critical voices’ to the debates surrounding AI vocal songs. To achieve this, the symposium features a diverse programme that includes:

(1) Keynote speech: Professor Ricardo Climent, Professor of Interactive Music and Director of the NOVARS Research Centre at the University of Manchester, will deliver an engaging keynote titled ‘How to get away with the Ocean of Data and sneak your creative voice’.

(2) Expert talks: Four invited speakers will share their insights:

- Dr Emmanouil Benetos (Queen Mary University of London): Perspectives on machine learning paradigms for analysing vocal music.

- Dr Robert Laidlow (University of Oxford): Reflections on compositional processes using language models as worldbuilding oracles.

- Dr Hedvig Jalhed (Lund University): Insights on creating characters and casting in AI-based opera.

- Dr Francesco Bentivegna (University of Bristol): Analysis of voice and AI in relation to storytelling myths.

(3) Paper presentations: A wonderful collection of over 15 papers around four key themes: Compositional practices & reflections; ethics & aesthetics of AI voice; machine learning, audio AI & AI-enhanced vocal performance; and legal & economic dimensions.

(4) Performances: The event features the premiere of Yūrei (Ghost) of the AI Empire, an immersive ‘science-fiction opera’ prototype by Alexandra Huang-Kokina and Atzi Muramatsu, alongside the performance of Post-Singularity Songs, composed by Dr Robert Laidlow.

Situated at the forefront of critical AI & music scholarship, this symposium aims to shape both the conceptual and practical development of future AI voice & vocal songs, ensuring that new AI tools reflect diverse and globally attuned cultural experiences and human values. A social evening with dinner and drinks will follow the conference.

The event is graciously supported by the Susan Manning Workshop Fund from IASH at the University of Edinburgh, the Digital Research Fund from Edinburgh Centre for Data, Culture, and Society (CDCS) and the Conference Grant from Royal Musical Association (RMA).

The event is also co-hosted and supported by the new research cluster ‘Creativity, AI, and the Human’ at the Edinburgh Futures Institute (EFI), led by Dr Caterina Moruzzi.

Host or Publisher Dr Alexandra Huang-Kokina