Research Fellow (RTDA), @IsplPolimi @polimi Machine Learning applied to Audio & Music (He/Him)
Milano, Italia
Joined September 2010
- Tweets34
- Following319
- Followers47
- Likes169
Luca Comanducci retweeted
Francesca Ronchini, Luca Comanducci, Simone Marcucci, Fabio Antonacci, "AI-Assisted Music Production: A User Study on Text-to-Music Models," arxiv.org/abs/2509.23364
Luca Comanducci retweeted
An urgent message from The Wire magazine
Running an independent music magazine is becoming increasingly difficult. We need your support
thewire.co.uk/in-writing/ess…
Glad to have been presented the FakeMusicCaps dataset and the risks and issues behind deepfake music detection!
Link to the paper --> arxiv.org/pdf/2409.10684
Link to the dataset --> zenodo.org/records/15063698
#AIMusic #GenerativeAI #Deepfake #AI #GenerativeMusic @IsplPolimi
The rise of text-to-music platforms like Suno and Udio has prompted researchers to develop systems that flag AI-generated music, @laur_insider reports. Test your own detection skills with our interactive game. scienceline.org/2025/05/ai-m…
Luca Comanducci retweeted
``Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models,'' Riccardo Passoni, Francesca Ronchini, Luca Comanducci, Romain Serizel, Fabio Antonacci, ift.tt/DNEBwqO
Luca Comanducci retweeted
``Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification,'' Francesca Ronchini, Ho-Hsiang Wu, Wei-Cheng Lin, Fabio Antonacci, ift.tt/CV32Urk
Luca Comanducci retweeted
``Towards HRTF Personalization using Denoising Diffusion Models,'' Juan Camilo Albarrac\'in S\'anchez, Luca Comanducci, Mirco Pezzoli, Fabio Antonacci, ift.tt/6sMuYmK
Luca Comanducci retweeted
I have shared our latest research, "Synthetic Training Set Generation Using #TextToAudio Models for Environmental #Sound Classification" at #DCASE2024 in Tokyo last month!
📝 Article: shorturl.at/0KW55
🔸 Slides: shorturl.at/oK0tP
Luca Comanducci retweeted
``FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models,'' Luca Comanducci, Paolo Bestagini, Stefano Tubaro, ift.tt/eiqoFjI
Luca Comanducci retweeted
``MambaFoley: Foley Sound Generation using Selective State-Space Models,'' Marco Furio Colombo, Francesca Ronchini, Luca Comanducci, Fabio Antonacci, ift.tt/dh1eEBF
Luca Comanducci retweeted
The #ICASSP2025 paper submission deadline is 9 September 2024. No new submissions will be accepted after this deadline. However, you may update the submitted paper until September 12. The title, author list and EDICS of the submitted paper cannot be changed.
Luca Comanducci retweeted
Our paper “Room Transfer Function Reconstruction Using #Complex-#Valued #Neural #Networks and Irregularly Distributed Microphones” will be presented at #EUSIPCO2024!
I won't be able to attend but DM me if you want to know more!
Preprint 👉 shorturl.at/MW8JZv
Luca Comanducci retweeted
Together with @LucaComan, we conducted a user experience study of #creative #interaction with #text-to-#music models to understand more about #human-#AI #collaboration with these tools.
Preprint: arxiv.org/pdf/2407.04333
Additional material: paguri-ismir-2024.github.io/…
(1/n)
Luca Comanducci retweeted
Interesting to see exploring the use of #AI-#generated #synthetic #data for various tasks. Can we trust them to train other models?
I've done a similar study in the #audio domain: arxiv.org/pdf/2403.17864
Our conclusions are similar, but the results are interesting!
Will training on AI-generated synthetic data lead to the next frontier of vision models?🤔
Our new paper suggests NO—for now. Synthetic data doesn't magically enable generalization beyond the generator's original training set.
📜: arxiv.org/abs/2406.05184
Details below🧵(1/n)
Luca Comanducci retweeted
``Synthetic training set generation using text-to-audio models for environmental sound classification,'' Francesca Ronchini, Luca Comanducci, Fabio Antonacci, ift.tt/piUXYv0
Luca Comanducci retweeted
``PAGURI: a user experience study of creative interaction with text-to-music models,'' Francesca Ronchini, Luca Comanducci, Gabriele Perego, Fabio Antonacci, ift.tt/TQZKjL5
Here is me presenting “Crafting Music and Audio via Textual Descriptions: exploring the Future Evolution of Music Production and Audio Content Generation” written with @FraRonchini.
youtube.com/live/2CUoe2YJ86g…
#AIMusic #AI #MusicAI #GenerativeMusic @IsplPolimi
Luca Comanducci retweeted
@LucaComan and I will present "Crafting Music and Audio via Textual Descriptions: Exploring the Future Evolution of Music Production and Audio Content Generation" tomorrow at "Artificial Creativity", Panel IV.
Livestream here 👉 youtube.com/watch?v=2CUoe2YJ…
I'll be presenting a paper on XAI and speech source localization at #ICASSP24 XAI-SA workshop (15/04) It will not be part of the proceedings, but you can find online
📜 paper arxiv.org/pdf/2404.03436.pdf
💻 code github.com/lucacoma/XAISrcLo…
📢 examples lucacoma.github.io/XAISrcLoc…
Luca Comanducci retweeted
Thrilled to share #Lyria, the world's most sophisticated AI music generation system. From just a text prompt Lyria produces compelling music & vocals. Also: building new Music AI tools for artists to amplify creativity in partnership w/YT & music industry deepmind.google/discover/blo…
@RBMA @nytimesmusic @robert_henke @haxan_cloak
is available a video of the performance? it would be really great!