Music Synthesis - Sound Examples
These sound examples were all generated with default settings, and run within one single application written in Cocoa under Mac OS X, with the Skeleton library.
Scrambled Music
This basic experiment relies on segmentation, based on an auditory spectrogram. Sounds are scrambled, and juxtaposed randomly. No cross-fading or overlap was used. The results aim to be artifact-free.Reversed Music
A simple structure is adopted. The segments are ordered from the last one to the first one. The audio however, is not reversed. This would be roughly equivalent to playing the score backwards.
By overlapping segments with each other, it is possible to speed up the music without processing the audio, and changing its pitch or timbre.
A beat tracker was implemented in order to define a metric to the music, where audio segments fit. A click track was added to the original music.
Similarly to "Scrambled Music", beat segments (as opposed to sound segments) are scrambled. The sensation of beat is maintained while the rest of the music is randomized.
Music naturally tends to repeat. A similarity measure between sound segments allows us to cluster them, and compress the audio in the time-domain. Artifacts, appear in the music domain as opposed to the audio domain.
When the similarity measure only takes into account the loudness function, musical variations at resynthesis are possible, in particular with the spectral content.
A database of sound segments is generated from the segmentation of a "source" piece. The database is used to resynthesize a "target" piece.