Method and system for energy-based song variant construction with demixing
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.
Claims2
A computerized method of generating a music work variant, comprising the steps of:
- (a) requiring a user to select a high energy level music work;
- (b) requiring the user to select a low energy level output work or a medium energy output work;
- (c) demixing the high energy level music work to create a vocal track, a drum track,
- and one other track different from said vocal track and said drum track;
- (d) if the user has selected said medium energy output work,
- (d1) reducing a volume of said drum track by 70%, thereby producing a reduced volume drum track, and
- (d2) reducing a volume of said voice track by 50%, thereby producing a reduced volume voice track,
- said reduced volume drum track, said reduced volume voice track, and
- said one other track different from said drum track and said vocal track together comprising a medium energy variant of said high energy music work;
- and
- (e) if the user has selected said low energy output work,
- (e1) reducing the volume of said drum track by 100%, thereby producing a lower volume drum track, and
- (e2) reducing the volume of said voice track by 80%, thereby producing a lower volume voice track,
- said lower volume drum track, said lower volume voice track, and said one other track different from said drum track and said vocal track together comprising a low energy variant of said high energy music work;
- and
- (f) if the user has selected said medium energy output work, performing at least a portion of said medium energy variant of said high energy level music work for the user,
- and
- if the user has selected said low energy output work, performing at least a portion of said low energy variant of said high energy level music work for the user.
A computerized method of generating a music work variant, comprising the steps of:
- (a) requiring a user to select a high energy level music work;
- (b) requiring the user to select a low energy level output work or a medium energy output work;
- (c) demixing the user selected high energy level music work to create at least three tracks, a vocal track, a drum track, and at least one track different from said vocal track and said drum track;
- (d) if the user has selected said medium energy output work,
- (d1) reducing a volume of said drum track by 70%, thereby producing a reduced volume drum track, and
- (d2) reducing a volume of said voice track by 50%, thereby producing a reduced volume voice track,
- said reduced volume drum track, said reduced volume voice track, and
- said at least one other track different from said vocal track and said drum track together comprising a medium energy variant of said high energy music work;
- and
- (e) if the user has selected said low energy output work,
- (e1) reducing the volume of said drum track by 100%, thereby producing a lower volume drum track, and
- (e2) reducing the volume of said voice track by 80%, thereby producing a lower volume voice track,
- said lower volume drum track, said lower volume voice track, and said at least one other track different from said vocal track and said drum track together comprising a low energy variant of said high energy music work;
- (f) if the user has selected said medium energy output work, performing at least a portion of said medium energy variant of said high energy level music work for the user,
- and
- if the user has selected said low energy output work, performing at least a portion of said low energy variant of said high energy level music work for the user.
Dependencies are inferred from the claim text.