This is a dataset of 22.5 hours of synthesized audio using the open-source learnfm clone of the DX7 FM synthesizer, based upon 31K presets from Bobby Blue. These represent "natural'' synthesis sounds---i.e.presets devised by humans.
The authors generated 4-second samples playing midi note 69 (A440) with a note-on duration of 3 seconds. For each preset, the authors varied only the velocity, from 1--127, and perceptually normalized the level of each sound. Sounds that were completely identical were removed from the dataset. DX7 FM synthesis is good for this purpose because it doesn't have a noise oscillator. Thus, for a particular preset, there is a timbral variation as the velocity increases. 8K presets had only one unique sound. The median was 51 unique sound per preset, mean 41.9, stddev 27.4.
Paper | Code | Results | Date | Stars |
---|