Back to results
US 11,996,071 B2Granted
Method and system for energy-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. Additionally, in some embodiments there is provided a method of energy-based song construction where the tracks of a multi-track work are balanced depending on the desired output volume level of the final project.
Claims15
A computerized method of generating an energy-based music work, comprising the steps of:
- (a) requiring a user to select a music style from among a plurality of music styles;
- (b) requiring the user to select at least one high energy seed part, where each of said at least one high energy seed parts comprises at least twelve channels;
- (c) requiring the user to select a medium energy level or a low energy level;
- (d) in a computer, said computer programmed to perform the steps comprising:
- (d1) for each of said at least one selected seed parts, if the user has selected said medium energy level, automatically disabling at least two channels in said selected seed part, thereby creating a processed selected seed part and
- (d2) for each of said at least one selected seed parts, if the user has selected said low energy level, automatically disabling at least four channels in said selected seed part, thereby creating said processed selected seed part;
- (d3) using an expert engine to automatically analyze each of said processed at least one selected seed part to produce a music work skeleton structure based on said selected music style and said at least one processed selected seed part;
- (d4) accessing an audio loop database containing a plurality of audio loops, each of said audio loops having a same loop style as said selected music style and each of said audio loops having a plurality of performance parameters associated therewith;
- (d5) using an AI system to select a plurality of audio loops from said audio loop database based on said plurality of performance parameters associated with each of said plurality of audio loops;
- (d6) using said AI system and said plurality of performance parameters associated with each of said selected plurality of audio loops to insert each of said selected audio loops into said music work skeleton structure, thereby forming said energy-based music work;
- and
- (d7) performing at least a portion of said energy-based music work for the user.
9 more elements
A computerized method of generating an energy-based music work, comprising the steps of:
- (a) requiring a user to select a music style from among a plurality of music styles;
- (b) requiring the user to select at least one high energy seed part from a plurality of high energy seed parts, wherein each of said high energy seed parts comprises six or more channels;
- (c) requiring the user to select a medium energy level or a low energy level;
- (d) in a computer, said computer programmed to perform the steps comprising:
- (d1) for each of said at least one selected seed parts, if the user has selected said medium energy level, automatically disabling at least two channels in said selected seed part, thereby creating a processed selected seed part and
- (d2) for each of said at least one selected seed parts, if the user has selected said low energy level, automatically disabling at least four channels in said selected seed part, thereby creating said processed selected seed part;
- (d3) using an expert engine to automatically analyze each of said processed at least one selected seed part to produce a music work skeleton structure based on said selected music style and said at least one processed selected seed part;
- (d4) accessing an audio loop database containing a plurality of audio loops, each of said audio loops having a same loop style as said selected music style and each of said audio loops having a plurality of performance parameters associated therewith;
- (d5) using an AI system to select a plurality of audio loops from said audio loop database based on said plurality of performance parameters associated with each of said plurality of audio loops;
- (d6) using said AI system and said plurality of performance parameters associated with each of said selected plurality of audio loops to insert each of said selected audio loops into said music work skeleton structure, thereby forming said energy-based music work;
- and
- (d7) performing at least a portion of said energy-based music work for the user.
9 more elements
A computerized method of generating an energy-based music work, comprising the steps of:
- (a) requiring a user to select a music style from among a plurality of music styles;
- (b) requiring the user to select at least one high energy seed part from a plurality of high energy seed parts, each of said plurality of seed parts comprising a plurality of channels;
- (c) requiring the user to select a medium energy level or a low energy level;
- (d) in a computer, said computer programmed to perform the steps comprising:
- (d1) for each of said at least one selected seed parts, if the user has selected said medium energy level, automatically disabling one or more of said at plurality of channels in said selected seed part to leave four of said plurality of channels unmuted, thereby producing a processed selected seed part,
- (d2) for each of said at least one selected seed parts, if the user has selected said low energy level, automatically disabling one or more of said at plurality of channels in said selected seed part to leave two of said plurality of channels unmuted, thereby producing a processed selected seed part,
- (d3) using an expert engine to automatically analyze each of said processed at least one selected seed part to produce a music work skeleton structure based on said selected music style and said at least one processed selected seed part;
- (d4) accessing an audio loop database containing a plurality of audio loops, each of said audio loops having a same loop style as said selected music style and each of said audio loops having a plurality of performance parameters associated therewith;
- (d5) using an AI system to select a plurality of audio loops from said audio loop database based on said plurality of performance parameters associated with each of said plurality of audio loops;
- (d6) using said AI system and said plurality of performance parameters associated with each of said selected plurality of audio loops to insert each of said selected audio loops into said music work skeleton structure, thereby forming said energy-based music work;
- and
- (d7) performing at least a portion of said energy-based music work for the user.
9 more elements
Dependencies are inferred from the claim text.