9GDB ( 9 genres database )

  • Description:
  • Corpus of chord progressions from nine different genres taken from three "domains": popular, jazz, and academic music. Popular music data have been separated into three sub-genres: pop, blues, and celtic (mainly Irish jigs and reels). For jazz, three styles have been established: a pre-bop class grouping swing, early, and Broadway tunes, bop standards, and bossanovas as a representative of latin jazz. Finally, academic music has been categorized according to historic periods: baroque, classicism, and romanticism.

ODB (onset detection database)

  • Description:
  • ODB is an onset detection test database built using a set of real recordings. This database contains some sounds selected from the RWC database and other real recordings. The songs were selected to cover a relatively wide range of instruments and musical genres.

JvC ( music genre recognition )

  • Description:
  • Automatic music genre recognition, either from audio or symbolic sources, is a much researched topic in the music information retrieval community. When dealing with symbolic music sources like digital scores or MIDI files, the main melody of a music piece is often clearly identified.
    This corpus contains melodies from jazz and classical music pieces encoded as MIDI file tracks.

Melody track recognition

  • Description:
  • A melody can be defined "melody" as a 'cantabile' sequence of notes, usually what a listener can remember of a song after hearing it, but this definition is not computable. MIDI files are organized by tracks containing one different voice each. A reliable system to identify the track containing the melody of a MIDI file is very relevant in music information retrieval for indexing and comparing music pieces.