Music generator
Techniques are disclosed relating to determining composition rules, based on existing music content, to automatically generate new music content. In some embodiments, a computer system accesses a set of music content and generates a set of composition rules based on analyzing combinations of multiple loops in the set of music content. In some embodiments, the system generates new music content by selecting loops from a set of loops and combining selected ones of the loops such that multiple ones of the loops overlap in time. In some embodiments, the selecting and combining loops is performed based on the set of composition rules and attributes of loops in the set of loops.
1. A method, comprising:
accessing, by a computer system, a set of music content;
generating, by the computer system, a set of composition rules based on analyzing combinations of a plurality of tracks in the set of music content, wherein the rules include rules for:
selecting a number of tracks to overlay such that they play at the same time;
selecting types of instruments from which to combine tracks; and
selecting a next key for key progression; and
generating, by the computer system, new output music content by selecting tracks from a set of tracks and combining selected ones of the tracks such that multiple ones of the tracks overlap in time, wherein the selecting and combining are performed based on the set of composition rules and attributes of tracks in the set of tracks.
2. The method of claim 1 , wherein the selecting and combining are further performed based on one or more target music attributes for the new output music content.
3. The method of claim 2 , further comprising:
adjusting at least one of the set of composition rules or the one or more target music attributes based on environment information associated with an environment in which the new output music content is played.
4. The method of claim 1 , wherein the generating the set of composition rules includes generating a plurality of different sets of rules for corresponding different types of instruments used for ones of the plurality of tracks.
5. The method of claim 1 , wherein the rules further include rules for:
selecting one or more types of instruments;
selecting one or more parameters for chopping vocal tracks;
selecting one or more low pass filter parameters; and
selecting one or more reverb parameters.
6. The method of claim 1 , wherein the rules further include one or more rules for:
whether to create energy by increasing tempo or adding complexity;
whether to transition by adding tracks or increasing gain;
ordering of tracks added for one or more transitions;
pitch transposition;
selecting a beat timing;
selecting one or more white noise parameters;
selecting a tempo; or
selecting a track based on audio amplitude in one or more frequency bins.
7. The method of claim 1 , wherein the generating the new output music content further includes modifying at least one of the tracks based on the set of composition rules.
8. The method of claim 1 , wherein one or more rules in the set of composition rules are specified statistically.
9. The method of claim 1 , wherein at least one rule in the rule set specifies a relationship between a target music attribute and one or more tracks attributes, wherein the one or more tracks attributes include one or more of: tempo, volume, energy, variety, spectrum, envelope, modulation, periodicity, rise time, decay time, or noise.
10. The method of claim 1 , wherein the set of music content includes content for a particular type of occasion.
11. The method of claim 1 , wherein the generating the set of composition rules includes training one or more machine learning engines to implement the set of composition rules, wherein the selecting and combining are performed by the one or more machine learning engines.
12. The method of claim 1 , wherein the set of composition rules includes multiple rule sets for specific types of tracks and a master rule set that specifies rules for combining different types of tracks.
13. A non-transitory computer-readable medium having instructions stored thereon that are executable by a computing device to perform operations comprising:
accessing a set of music content;
generating a set of composition rules based on analyzing combinations of a plurality of tracks in the set of music content, wherein the rules include rules for:
selecting a number of tracks to overlay such that they play at the same time;
selecting types of instruments from which to combine tracks; and
selecting a next key for key progression; and
generating new output music content by selecting tracks from a set of tracks and combining selected ones of the tracks such that multiple ones of the tracks overlap in time, wherein the selecting and combining are performed based on the set of composition rules and attributes of tracks in the set of tracks.
14. The non-transitory computer-readable medium of claim 13 , wherein the selecting and combining are further performed based on one or more target music attributes for the new output music content.
15. The non-transitory computer-readable medium of claim 14 , wherein the operations further comprise:
adjusting at least one of the set of composition rules or the one or more target music attributes based on environment information associated with an environment in which the new output music content is played.
16. The non-transitory computer-readable medium of claim 13 , wherein the generating the set of composition rules includes generating a plurality of different sets of rules for corresponding different types of instruments used for ones of the plurality of tracks.
17. The non-transitory computer-readable medium of claim 13 , wherein the rules further include rules for:
selecting one or more types of instruments;
selecting one or more parameters for chopping vocal tracks;
selecting one or more low pass filter parameters;
selecting one or more reverb parameters;
whether to create energy by increasing tempo or adding complexity;
whether to transition by adding tracks or increasing gain;
ordering of tracks added for one or more transitions;
pitch transposition;
selecting a beat timing;
selecting one or more white noise parameters;
selecting a tempo; and
selecting a track based on audio amplitude in one or more frequency bins.
18. The non-transitory computer-readable medium of claim 13 , wherein at least one rule in the rule set specifies a relationship between a target music attribute and one or more tracks attributes, wherein the one or more tracks attributes include one or more of: tempo, volume, energy, variety, spectrum, envelope, modulation, periodicity, rise time, decay time, or noise.
19. The non-transitory computer-readable medium of claim 13 , wherein the generating the set of composition rules includes training one or more machine learning engines to implement the set of composition rules, wherein the selecting and combining are performed by the one or more machine learning engines.
20. An apparatus, comprising:
one or more processors; and
one or more memories having program instructions stored thereon that are executable by the one or more processors to:
access a set of music content;
generate a set of composition rules based on analyzing combinations of a plurality of tracks in the set of music content, wherein the rules include rules for:
selecting a number of tracks to overlay such that they play at the same time;
selecting types of instruments from which to combine tracks; and
selecting a next key for key progression; and
generate new output music content by selecting tracks from a set of tracks and combining selected ones of the tracks such that multiple ones of the tracks overlap in time, wherein the selecting and combining are performed based on the set of composition rules and attributes of tracks in the set of tracks.