Back to results
US 2020/0090632 A1Published application
Method and system for hybrid ai-based song construction
AssigneeBellevue Investments GmbH & Co. Kgaa
InventorsDIETER REIN, JURGEN JARON
Life of this patent
Estimating the term…
Abstract
According to an embodiment, there is provided a system and method for automatic AI-based song construction based on ideas of a user. It provides and benefits from a combination of expert knowledge resident in an expert engine which contains rules for a musically correct song generation and machine learning in an AI-based audio loop selection engine for the selection of fitting audio loops from a database of audio loops.
Claims13
A method of hybrid AI/expert engine-based song generation, comprising the steps of:
- (a) requiring a user to select a music style from among a plurality of music styles and at least one song part;
- (b) using an expert engine to automatically analyze said selected at least one song part to produce a song skeleton structure based on said selected music style and said at least one song part;
- (c) using an AI system to select a plurality of audio loops from an audio loop database for insertion into said song skeleton structure, each of said audio loops in said audio loop database having a plurality of performance parameters associated therewith, said AI system selecting said plurality of audio loops for insertion using at least said plurality of performance parameters associated with each audio loop in said database;
- (d) inserting said selected audio loops into said generated song skeleton structure, thereby generating a music work;
- and
- (e) performing at least a portion of said music work for the user.
3 more elements
A method of hybrid AI/expert engine-based song generation, comprising the steps of:
- (a) allowing a user to select a plurality of loops from a loop database for inclusion in a musical work, thereby producing a first song part, each of said loops in said loop database having a plurality of performance parameters associated therewith;
- (b) determining a music style associated with said first song part from among a plurality of provided song styles;
- (c) using an expert engine to automatically analyze said first song part to produce a song skeleton structure based on said determined music style and said first song part;
- (d) using an AI system to select a plurality of audio loops from said audio loop database for insertion into said song skeleton structure, said AI system selecting said plurality of audio loops for insertion using at least said plurality of performance parameters associated with each audio loop in said loop database;
- (e) inserting said selected audio loops into said generated song skeleton structure, thereby generating the music work;
- and
- (f) performing at least a portion of said music work for the user.
4 more elements
Dependencies are inferred from the claim text.