Jukebox
A prominent approach is to generate music symbolically in the form of a piano roll, which specifies the timing, pitch, velocity, and instrument of each note to be played. This has led to impressive results like producing Bach chorals, polyphonic music with multiple instruments, as well as minute long musical pieces. But symbolic generators have limitations--they cannot capture human voices or many of the more subtle timbres, dynamics, and expressivity that are essential to music. A different approach[1] is to model music directly as raw audio. Generating music at the audio level is challenging since the sequences are very long.
May-1-2020, 10:39:13 GMT