Category Research

The 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART), part of Evostar, took place in Trieste, Italy, between 23 and 25 April 2025.

We are pleased to announce that the following paper, authored by AIM PhD student Keshav Bhandari, received the best paper award!

Yin-Yang: Developing Motifs With Long-Term Structure And Controllability, Keshav Bhandari, Geraint A. Wiggins, Simon Colton

Yin-Yang is a neuro-symbolic framework that combines three transformer models to generate structured melodies with coherent long-term development, while allowing user control over musical themes and variations.

On 24-28 April, AIM researchers will participate at the Thirteenth International Conference on Learning Representations (ICLR 2025), taking place in Singapore. ICLR is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning.

AIM members will be presenting the following papers at the main track of ICLR 2025:

• Aria-MIDI: A Dataset of MIDI Files for Symbolic Music Modeling, by Louis Bradshaw, Simon Colton
• MuPT: A Generative Symbolic Music Pretrained Transformer, by Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, Xinrun Du, Shuyue Guo, Yiming Liang, Yizhi Li, Shangda Wu, Junting Zhou, Tianyu Zheng, Ziyang Ma, Fengze Han, Wei Xue, Gus Xia, Emmanouil Benetos, Xiang Yue, Chenghua Lin, Xu Tan, Wenhao Huang, Jie Fu, Ge Zhang

See you all at ICLR!

On 6-11 April 2025, several AIM researchers will participate at the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025). ICASSP is the leading conference in the field of signal processing and the flagship event of the IEEE Signal Processing Society.

As in previous years, AIM will have a strong presence at the conference, both in terms of numbers and overall impact. The below papers authored or co-authored by AIM members will be presented at the main ICASSP 2025 track:

• Evaluating contrastive methodologies for music representation learning using playlist data, by Gregor Meehan, Johan Pauwels
• GraFPrint: a GNN-based approach for audio identification, by Aditya Bhattacharjee, Shubhr Singh, Emmanouil Benetos
• Hybrid losses for hierarchical embedding learning, by Haokun Tian, Stefan Lattner, Brian McFee, Charalampos Saitis
• Learning music audio representations with limited data, by Christos Plachouras, Emmanouil Benetos, Johan Pauwels
• Leave-One-EquiVariant: alleviating invariance-related information loss in contrastive music representations, by Julien Guinot, Elio Quinton, György Fazekas
• LHGNN: local-higher order graph neural networks for audio classification and tagging, by Shubhr Singh, Emmanouil Benetos, Huy Phan, Dan Stowell
• LLaQo: towards a query-based coach in expressive performance assessment, by Huan Zhang, Vincent K.M. Cheung, Hayato Nishioka, Simon Dixon, Shinichi Furuya
• Music2Latent2: audio compression with summary embeddings and autoregressive decoding, by Marco Pasini, Stefan Lattner, György Fazekas
• Towards an integrated approach for expressive piano performance synthesis from music scores, by Jingjing Tang, Erica Cooper, Xin Wang, Junichi Yamagishi, György Fazekas

See you in Hyderabad!