CCCB: Artificial Intelligence Exhibition

CCCB: Artificial Intelligence Exhibition

A six-month interactive installation at the Centre de Cultura Contemporània de Barcelona in which over 3,000 members of the public engaged with a generative sonic system.

Installation Interactive Generative Public-Engagement
Status: Finished, no active maintenance

content

Overview

Centre de Cultura Contemporània de Barcelona (CCCB) hosted a six-month long exhibition on Artificial Intelligence:

More about the program


For this exhibition, we prepared an interactive installation in which the public could interact with some of the latest rhythm generation models we had developed.

The main idea for the installation was to provide a MIDI Bongo interface to allow users to record rhythmic loops, using which the system would generate accompanying drum patterns.

As a secondary objective of the installation, we crowdsourced a dataset of rhythmic improvisations from various expertise levels.

To read more about the dataset, read the following post:

El Bongosero

El Bongosero

A Dataset of Hand-Played Bongo Grooves Accompanying Drum Patterns

Dataset Bongo Percussion Interactive-Installation
Dataset Oct 2023


We have also written a paper going into more details about the installation and the dataset, which you can read here:

  1. El Bongosero: A Crowd-sourced Symbolic Dataset of Improvised Hand Percussion Rhythms Paired with Drum Patterns

    El Bongosero: A Crowd-sourced Symbolic Dataset of Improvised Hand Percussion Rhythms Paired with Drum Patterns

    Nicholas Evans*, Behzad Haki*, Daniel Gomez, and 1 more

    * Equal contribution

    Proceedings of the 24th International Society for Music Information Retrieval Conference · 2024
    PDFWebsiteSlidesPoster
    Abstract

    We present El Bongosero, a large-scale, open-source symbolic dataset comprising expressive, improvised drum performances crowd-sourced from a pool of individuals with varying levels of musical expertise. Originating from an interactive installation hosted at Centre de Cultura Contemporània de Barcelona, our dataset consists of 6,035 unique tapped sequences performed by 3,184 participants. To our knowledge, this is the only symbolic dataset of its size and type that includes expressive timing and dynamics information as well as each participant’s level of expertise. These unique characteristics could prove to be valuable to future research, particularly in the areas of music generation and music education. Preliminary analysis, including a step-wise Jaccard similarity analysis on a subset of the data, demonstrate that this dataset is a diverse, nonrandom, and musically meaningful collection. To facilitate prompt exploration and understanding of the data, we have also prepared a dedicated website and an open-source API in order to interact with the data.

    BibTeX 
    @inproceedings{Haki2024ELBNG,
  title = {{El Bongosero: A Crowd-sourced Symbolic Dataset of Improvised Hand Percussion Rhythms Paired with Drum Patterns}},
  author = {Evans, Nicholas and Haki, Behzad and Gomez, Daniel and Jorda, Sergi},
  booktitle = {{Proceedings of the 24th International Society for Music Information Retrieval Conference}},
  year = {2024},
  month = nov,
  publisher = {ISMIR},
}