Category Research

Melodies of popular songs have become simpler since the 1950s, according to a study carried out by AIM PhD student Madeline Hamilton and C4DM academic Dr Marcus Pearce, published in the journal Scientific Reports. The full paper can be found at: https://www.nature.com/articles/s41598-024-64571-x

An analysis of hundreds of chart hits from the past 70 years has shown “a significant decline” in the complexity of rhythm and pitch in song melodies. They said the biggest transitions – or “bursts of change” – occurred in the years 1975 and 2000 – when music genres such as new wave, disco and stadium rock started gaining popularity in the mid-1970s, and hip-hop became more prominent in the early Noughties. The researchers said the findings suggest complexity and creative expression in popular music is shifting away from melody and towards other elements such as quality of the sound.

See the full newsitem published in the Independent: https://www.independent.co.uk/arts-entertainment/music/news/top-song-melodies-simpler-study-b2574633.html

On 1-2 July 2024, AIM PhD student Jiawen Huang will participate at the UK and Ireland Speech Workshop (UKIS 2024). The UK and Ireland Speech Workshop aims to bring together researchers within the UK and Ireland’s Speech Science and Speech Technology community, both in academia and industry. UKIS 2024 is organised by the Speech Research Group, Department of Engineering, University of Cambridge in collaboration with the UK Speech Community. The below work will be presented at UKIS 2024:

• Multilingual Integration in Lyrics Transcription: Data, Language Conditioning, and Transliteration Augmentation, by Jiawen Huang and Emmanouil Benetos

See you all at UKIS!

On 23rd-26th June, several AIM PhD students will participate in the 16th ACM Conference on Creativity and Cognition 2024 (C&C 2024). C&C is a leading international conference that brings together researchers and practitioners from various disciplines to explore technologies wide impacts on creativity, from designing and working with AI tools, to the social and cultural aspects of creativity.

The following paper received an honorable mention award at the conference:

• Reflection Across AI-based Music Composition, by Corey Ford, Ashley Noel-Hirst, Sara Cardinale, Jackson Loth, Pedro Sarmento, Elizabeth Wilson, Lewis Wolstanholme, Kyle Worrall and Nick Bryan-Kinns.

The paper collects first-person accounts, interview and questionnaire measures, on how several AIM and C4DM researchers used AI tools of their choice in their music making, contributing descriptions of how they reflected when using AI generated content.

AIM members Ashley Noel-Hirst and Corey Ford are also co-authors of the paper:

• Using Incongruous Genres to Explore Music Making with AI Generated Content, by Nick Bryan-Kinns, Ashley Noel-Hirst, and Corey Ford.

The paper explores how an AI tool trained on a Folk dataset is used and appropriated by musicians in the genres of both, as a playful way to explore Human-AI Interaction.

The 2nd international workshop on eXplainable AI for the Arts is also run at the conference, co-organized by AIM members Corey Ford and Shuoyang Zheng. This workshop examines the challenges and opportunities at the intersection of explainable AI and the Arts, offering a critical view on the explainable aspects of Responsible AI and Human-Centred AI. With an accepted paper from AIM of:

• A Mapping Strategy for Interacting with Latent Audio Synthesis Using Artistic Materials by Shuoyang Zheng, Anna Xambó Sedó and Nick Bryan-Kinns.

The paper describes how mapping sketches to the latent space of the audio synthesis RAVE model can be used to support temporal and cross-modal aspects of explainable AI. See this paper alongside other proceedings at https://xaixarts.github.io/2024

Corey Ford is also on the organising committee as a chair for Student Volunteers.

We hope to see you all at ACM C&C!