CV
Contact Information
| Name | Michele Buccoli |
| Professional Title | Senior Audio Scientist |
| michele.buccoli@outlook.it |
Professional Summary
Senior audio scientist specialized in speech audio signals for low-cost applications
Experience
-
2019 - present Milan, Italy
Sr Innovation Scientist
BdSound S.r.l.
Co-lead the innovation department of BdSound, coordinating the machine learning team, consultancy with customers for DSP expertise, support to academic papers.
- DSP and ML-based algorithm design
- mentoring to jr engineerss
- relationship with academia and customers
- scouting for new technologies
- support for technical HR
-
2016 - 2018 Milan, Italy
postdoc researcher
Politecnico di Milano
Participation to projects WhoLoDance and InterMusic
- dance analysis
- remote music performance
-
2013 - 2013 Milan, Italy
Intern
ST MicroElectronics
- internship on the active noise cancellation
Education
-
2013 - 2016 Milan, Italy
PhD
Politecnico di Milano
TLC Engineering
- Music Information Retrieval
- Machine and Deep Learning
- low level features analysis
- musical structural segmentation
- automatic semantic description
-
2010 - 2013 Milan, Italy
M. Sc. Engineering
Politecnico di Milano
Computer Engineering - Sound and Music
-
2007 - 2010 Pisa, Italy
B. Sc. Engineering
Università di Pisa
Computer Engineering
Projects
-
WhoLoDance
part of the Horizon2020 WholoDance, which sought to bridge the gap between traditional dance practice and cutting-edge technology. The project’s primary goal was to digitize and preserve the “intangible cultural heritage” of dance while creating smart, interactive tools for teaching, learning, and choreography.
- dance motion capture analysis
- alignment of dance motion capture and video signals
- design and development of annotation tools for dance sequences
-
Intermusic
the INTERMUSIC project aimed to create a high-quality online environment for remote music education, specializing in low-latency technology for real-time rehearsals and performances. It was coordinated by the Conservatorio di Musica “Giuseppe Verdi” di Milano in partnership with Politecnico di Milano, the Royal Danish Academy of Music, and the Lithuanian Academy of Music and Theatre. The ultimate goal was to integrate blended learning into European higher education to foster international collaboration while reducing travel costs and environmental impact.
- dance motion capture analysis
- alignment of dance motion capture and video signals
- design and development of annotation tools for dance sequences
Publications
-
2017 Linking signal and semantic representations of musical content for music information retrieval
Politecnico di Milano
A unified framework is proposed to connect low‑level audio signal features with high‑level semantic descriptions, enabling more effective music information retrieval across tasks like structure analysis, bootleg detection, timbre annotation, and natural‑language music search.
-
2015 Feature-based analysis of the effects of packet delay on networked musical interactions
Journal of the Audio Engineering Society
-
2019 Virtual reality and choreographic practice: The potential for new creative methods
Body, Space & Technology
-
2019 A Presence- and Performance-Driven Framework to Investigate Interactive Networked Music Learning Scenarios
Wireless Communications and Mobile Computing
-
2013 A music search engine based on semantic text-based query
2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)
-
2014 Unsupervised feature learning for bootleg detection using deep learning architectures
2014 IEEE International Workshop on Information Forensics and Security (WIFS)
-
2015 A dimensional contextual semantic model for music description and retrieval
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
-
2015 An unsupervised approach to the semantic description of the sound quality of violins
2015 23rd European Signal Processing Conference (EUSIPCO)
-
2016 Unsupervised feature learning for music structural analysis
2016 24th European Signal Processing Conference (EUSIPCO)
-
2016 A Higher-Dimensional Expansion of Affective Norms for English Terms for Music Tagging
Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR)
-
2017 Using multi-dimensional correlation for matching and alignment of mocap and video signals
2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)
-
2018 Beat tracking using recurrent neural network: a transfer learning approach
2018 26th European Signal Processing Conference (EUSIPCO)
-
2018 Investigating networked music performances in pedagogical scenarios for the intermusic project
2018 23rd Conference of Open Innovations Association (FRUCT)
-
2018 Time is not on my side: network latency, presence and performance in remote music interaction
XXII Colloquio di Informatica Musicale (CIM)
-
2019 Automatic playlist generation using Convolutional Neural Networks and Recurrent Neural Networks
2019 27th European Signal Processing Conference (EUSIPCO)
-
2023 Real-Time Multichannel Speech Separation and Enhancement Using a Beamspace-Domain-Based Lightweight CNN
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
-
2024 An empirical evaluation of in-car acoustic measurements for the sports car scenario
2024 AES 5th International Conference on Automotive Audio
-
2024 Audio speech source separation and enhancement in an automotive scenario using different microphone configurations
2024 AES 5th International Conference on Automotive Audio
-
2025 A Small-Footprint Deep-Learning Solution for Real-Time In-Car Emergency Vehicle Detection
2025 33rd European Signal Processing Conference (EUSIPCO)
-
2025 Effects of automotive microphone frequency response characteristics and noise conditions on speech and ASR quality--an experimental evaluation
2025 AES International Conference