The lab has two Honourable Mention papers at #CHI2024, both in this online session on 15 May: programs.sigchi.org/chi/2024/progr… and both exploring the theory and practice of entanglement HCI (thread)

biiiiiiig 🤘

I’m at Berklee College of Music this weekend, presenting my work ‘Advancing AI in Music Composition: Refining the Generative Music Overpainting Task’ at the 1st AES Symposium of AI and the Musician! Really happy and excited to be here - hmu if you’d like to connect!😊🇺🇸🎶

Very happy to have two papers accepted at ISMIR Conference this year, one on benchmarking audio-language models for music understanding and another on efficient music-text representation learning, presenting work done during my internship at Adobe Research. Preprints coming soon!

Beautiful performance by Gamelan Sekar Petak at ESCOM12 -- where yesterday I presented initial ethnographic work on #timbre thinking in musical craft practice w/ Bleiz Del Sette Jordie Shier Haokun Tian Stay tuned for the video link! C4DM at QMUL

Our member Ilaria Manco will present her recent work in multimodal audio-language models at the DMLR workshop, a satellite event of ICML Conference this week. Please check it out if you're at ICML! aim.qmul.ac.uk/aim-at-dmlr-ic…

🚨 Call for Papers: First AES International Conference on Artificial Intelligence and Machine Learning for Audio (AIMLA 2025), Queen Mary University of London, Sept. 8-10, 2025. c4dm.eecs.qmul.ac.uk/news/2024-07-2…

Thrilled to present my recent research at the Audio Programmer Interface (API) London meetup on August 30th! Honored to be part of such an amazing lineup of audio developers. Who else is attending? Look forward to connecting! api-london.eventbrite.com

Excited to share the pre-print of midi2tab: arxiv.org/pdf/2408.05024 w/ Xavier Riley + Pedro Sarmento. Here is an audio-to-midi-to-tab demo using our previous High-Resolution Guitar Transcription model and our MIDl-to-Tab Transformer. See you in SF, #ismir2024! 👋 C4DM at QMUL ISMIR Conference