the great archive

Publications

Papers, datasets, demos and talks.

Papers

Datasets

Musical performance datasets for expressive variation modeling, pattern recognition and groove analysis. All share a unified artist ID namespace and flat file naming scheme.

MIDI · Monophonic · Melodic

DoMP

4,392 files40 performers333 patternsPiano & guitar

Dataset of Monophonic Patterns. MIDI recordings of monophonic melodic patterns performed by 40 anonymous musicians (20 pianists, 20 guitarists). Each pattern family has one ground-truth reference and multiple expressive variations in timing, dynamics, articulation and ornamentation. Mean 13.2 versions per pattern (range 4–32). Designed for expressive music generation, variation modeling and monophonic performance analysis.

Zenodo ↗
Audio · Polyphonic · WAV

DoPP

2,276 files20 performers176 patternsPiano & guitar

Dataset of Polyphonic Patterns. Mono audio recordings (WAV, 48 kHz, 16-bit PCM) of expressive performances by 20 anonymous musicians (10 pianists, 10 guitarists). Each pattern family pairs a ground truth with expressive variations spanning ornamental, harmonic and structural divergence; 89.3% of variation pairs remain harmonically close (chroma similarity > 0.9). Mean duration 5.2 s. Designed for audio-domain expressive performance analysis and generation.

Zenodo ↗
MIDI · Drums · Rhythmic

DoDP

994 files8 performers77 patternsPercussion

Dataset of Drum Patterns, v1. MIDI recordings of rhythmic drum patterns by 8 anonymous percussionists using GM standard drum notes. Each pattern family pairs one ground truth with expressive variations in timing, velocity, density and instrumentation. Mean 12.9 versions per pattern (range 10–51). Files mix ticks-per-beat (480 or 960) and drum channel (0 or 9) due to differing DAW export settings; both are documented in metadata. For drum pattern generation, groove analysis and rhythmic variation modeling.

Zenodo ↗
MIDI · Drums · Rhythmic

DoDP2

2,177 files10 performers100 patternsPercussion

Dataset of Drum Patterns, v2. Complementary to DoDP: 10 anonymous percussionists, uniform MIDI encoding (96 ticks/beat, channel 0) and compact loop patterns (mean 3.9 beats). Denser sampling, mean 21.8 versions per pattern (range 19–59). Introduces artist-level template patterns (patternID = -1), 194 files representing each performer's baseline rhythmic character, usable as style anchors or zero-shot conditions. For groove modeling, style transfer and densely-sampled rhythmic variation research.

Zenodo ↗

PhD Defense

Embedded Real-Time Musical Pattern Detection for Smart Musical Instruments

Public defense of my PhD thesis, 31/01/2025, University of Trento, Italy.

Demos & Concerts

Smart musical instruments and real-time musical pattern detection in performance.

An Internet of Musical Things Performance Ecosystem Based on Real-Time Musical Pattern Recognition

Live performance showing smart instruments triggering lights, visuals and devices via embedded pattern detection.

Multisensory Concert Enabled by Smart Musical Instruments and Real-Time Musical Pattern Detection

Concert where musical patterns control stage lights, smoke, MR visuals and haptic feedback for the audience.

Real-Time Monophonic Pattern Recognition System Based on MIDI Data

Technical demo of the symbolic (MIDI-based) real-time pattern recognition system used as an early prototype.

Hot Licks: a real-time pattern detection system for MIDI instruments

The pattern detection system in operation; linked from the JAES paper write-up.

MIDI Innovation Awards 2023 highlights

Event video from the MIDI Innovation Awards 2023, where an early prototype from this research was a finalist.

Short Papers, Talks & Demos

  • 2025 · Oct
    Demo of a Smart Musical Instrument-Based Real Time Pattern Detection System
    IS2 2025, L'Aquila, Italy
  • 2025 · Sep
    Demo of a Smart Musical Instrument to Control Peripheral Devices
    Notte della Ricerca, MUSE, Trento, Italy
  • 2025
    Mixed Reality Demo for Smart Musical Instruments and the Musical Metaverse
    Kickoff Meeting for the Musical Metaverse, University of Trento, Italy
  • 2024 · Oct
    University of Trento, Italy
  • 2024 · Sep
    Demo of a Smart Musical Instrument-Based Real Time Pattern Detection System
    Audio Mostly Conference, University of Milan, Italy
  • 2024 · Sep
    Demo of a Smart Musical Instrument-Based Real Time Pattern Detection System
    ICT Days, University of Trento, Italy
  • 2024 · May
    Real Time Musical Pattern Detection
    McGill University, Canada
  • 2024 · May
    University of Trento, Italy
  • 2023 · Oct
    Demo of a Smart Musical Instrument to Control Peripheral Devices
    ISMIR Conference, Politecnico di Milano, Italy
  • 2023 · Oct
    Demo of a Smart Musical Instrument to Control Peripheral Devices
    SoundMIT Synth Expo, Turin, Italy
  • 2023 · Sep
    University of Trento, Italy

Scientific Committees & Review

  • IEEE Access
  • Journal of the National Science Foundation – Sri Lanka
  • IEEE Internet of Sounds Symposium
  • Immersive and 3D Audio conference
  • XXIII Colloquio di Informatica Musicale