Matteo Spanio

Centro di Sonologia Computazionale.

Department of Information Engineering.

iome_bn.jpg

CSC lab, building DEI/S

Via Gardenigo 6/A

Padua, Italy

Hi there, I’m Matteo Spanio, Ph. D. student at the University of Padua. I’m interested in:

  • 🤖 machine learning,
  • 📡 signal processing,
  • 🎹 music.

My Ph. D. project focuses on studying deep learning methods for music generation based on cross modal perception.

I’m member of the MPAI group, the international, unaffiliated, no-profit organisation developing standards for AI-based data coding.

I’m also a musician, and I play the clarinet on a regular basis in many orchestras and ensembles (Orchestra di Padova e del Veneto, Orchestra del Friuli Venezia Giulia, Orchestra San Marco, Concordia Chamber Orchestra, Rossini Ensemble and many others).

To see my work, check out my projects and publications. Time permitting, I also write blog posts.

news

Aug 28, 2025 Next week I’ll present torchfx, a new python library for GPU accelerated audio effects, at DAFx 2025 in Ancona, Italy. The conference will take place from 2 to 6 September 2025. Hope to see you there!
Mar 05, 2025 I am happy to announce the release of a our new deep learning model for synesthetic music generation. It is available for download on Hugging Face. Learn more about it in our preprint paper. Enjoy!
Nov 03, 2024 My two new papers Towards Emotionally Aware AI: Challenges and Opportunities in the Evolution of Multimodal Generative Models and Filming the sound: Anomaly Detection on Audio Tape Recordings using Computer Vision Algorithms have been accepted for publication at the 23rd International Conference of the Italian Association for Artificial Intelligence that will take place in Bozen between 25 and 28 november. See you there!
Aug 18, 2024 A new paper titled A novel derivative-based approach for the automatic detection of time-reversed audio in the MPAI/IEEE-CAE ARP international standard by Marina Bosi, Fabio Zanini, Alessandro Russo, Sergio Canazza and me has been accepted at the AES Show 2024 that will take place in New York from 8 to 10 October 2024. See you in New York!
Jun 01, 2024 I will attend the 7th Advanced Course on Data Science & Machine Learning (ACDL) from 10 to 14 june. See you there!

latest posts

selected publications

  1. Enhancing Preservation and Restoration of Open Reel Audio Tapes Through Computer Vision
    Alessandro Russo, Matteo Spanio, and Sergio Canazza
    In Image Analysis and Processing - ICIAP 2023 Workshops, 2024
  2. AES
    aes2024.jpg
    A novel derivative-based approach for the automatic detection of time-reversed audio in the MPAI/IEEE-CAE ARP international standard
    Marina Bosi, Fabio Zanini, Matteo Spanio, and 2 more authors
    Journal of the Audio Engineering Society, 2024
  3. Frontiers in CS
    frontiers2025.webp
    A multimodal symphony: integrating taste and sound through generative AI
    Matteo Spanio, Massimiliano Zampini, Antonio Rodà, and 1 more author
    Frontiers in Computer Science, 2025