US 12,170,075 B2
Comparison training for music generator
Edward Balassanian, Austin, TX (US); Patrick E. Hutchings, Melbourne (AU); and Toby Gifford, Melbourne (AU)
Assigned to AiMi Inc., Littleton, CO (US)
Filed by AiMi Inc., Littleton, CO (US)
Filed on Aug. 20, 2021, as Appl. No. 17/408,076.
Claims priority of provisional application 63/068,431, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,433, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,436, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,411, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,415, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,421, filed on Aug. 21, 2020.
Claims priority of provisional application 63/068,426, filed on Aug. 21, 2020.
Prior Publication US 2022/0059062 A1, Feb. 24, 2022
Int. Cl. G10H 1/00 (2006.01); G06N 20/00 (2019.01); G10H 1/053 (2006.01)
CPC G10H 1/0025 (2013.01) [G06N 20/00 (2019.01); G10H 1/053 (2013.01); G10H 2210/031 (2013.01); G10H 2210/105 (2013.01); G10H 2210/111 (2013.01); G10H 2220/116 (2013.01); G10H 2240/125 (2013.01); G10H 2240/131 (2013.01); G10H 2240/141 (2013.01); G10H 2240/325 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, by a music generator on a computer system, output music content from a plurality of digital music fragments, wherein the output music content includes an array of different output music content generated from the plurality of digital music fragments, and wherein the music generator generates the array of different output music content in audio format by sequentially interpreting one or more music generation parameters following a set of interpretation rules;
receiving, by the music generator, reinforcement input determined from the generated output music content;
adjusting, using an algorithm, at least one of the one or more music generation parameters for the music generator based on the reinforcement input, wherein the one or more music generation parameters include at least one of previously generated music generation parameters or user-created music generation parameters; and
generating new output music content from the plurality of digital music fragments based on the adjusted at least one of the one or more music generation parameters.