Computer Music Laboratory
Automatic composition has been the area where computers have
played a significant role traditionally, but now other areas related to
human cognition have been introduced, like music categorization,
performance, indexing and retrieval, music document analysis, perception of key, rhythm,
meter, style, etc. In all these tasks pattern recognition and machine
learning techniques have shown to be useful and that is our work domain.
Active lines of work
Symbolic music style recognition
With applications like the indexation and exploration of
music databases, genre analysis, or authoring. Statistical techniques are
being applied to digital scores for this task.
Music encoding and cultural heritage
Grammars and libraries for encoding and decoding different symbolic music
languages. Optical music recognition. Hand-written recognition. Early music
notations. Translation from old notations to modern music representations.
"Plain and easie
code" ANTLR v4 grammar
MEI Customisation for Hierarchical Analysis
Automatic transcription of digital audio
Extracting a symbolic representation (score) from musical signals.
The polyphonic and polytimbral tasks are open
problems in signal processing research. The role of human feedback in
interactions and multimodality are being studied.
Automatic music analysis
Melodic, harmonic, and functional analysis are powerful tools for music
segmentation, key identification and tracking, music comparison, chordal
progressions, reductions, performance rendering, etc.
Track identification in multi-track MIDI files
Automatically identifying the track containing a particular line or voice in a MIDI
file, with straightforward applications in music retrieval and
Music similarity metrics
The key tool for music comparisons. Data structures suitable to represent
music data and probabilistic apporaches are explored.
One of the classical tasks in computer music and artificial intelligence.
Music representation and pattern recognition methods are
used for style-guided composition through evolutionary methods.
Paper in Music-AI Workshop, IJCAI 2007. Demos.
Digital sound synthesis
Techniques for using computers to sound generation, involving computer
languages like Csound. Control sequencies generation for performance
rendering and music composition.