# US 2021/0241734 A1 · Systems, devices, and methods for computer-generated musical note sequences

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0241734 A1
- Document ID: US20210241734A1
- Status: Published application
- Kind: A1
- Application number: 17/163,214
- Filed: 2021-01-29
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Obeebo Labs Ltd.
- Applicants: Obeebo Labs Ltd.
- Inventors: Colin P. Williams
- Web page: https://patentgrep.com/patent/US20210241734A1

## CPC

- G10H 1/0025: {Automatic or semi-automatic music composition, e.g. producing random music, applying rules from music theory or modifying a musical piece (automatically producing a series of tones G10H1/26)}
- G06F 16/65: Clustering; Classification
- G06Q 40/12: Accounting
- G06Q 50/184: {Intellectual property management}
- G10H 1/0008: {Associated control or indicating means}
- G10H 1/0041: {in coded form}
- G10H 7/08: by calculating functions or polynomial approximations to evaluate amplitudes at successive sample points of a tone waveform
- G10H 2210/031: Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
- G10H 2210/056: for extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres
- G10H 2210/061: for extraction of musical phrases, isolation of musically relevant segments, e.g. musical thumbnail generation, or for temporal structure analysis of a musical piece, e.g. determination of the movement sequence of a musical work
- G10H 2210/071: for rhythm pattern analysis or rhythm style recognition
- G10H 2210/076: for extraction of timing, tempo; Beat detection
- G10H 2210/111: Automatic composing, i.e. using predefined musical rules
- G10H 2210/131: Morphing, i.e. transformation of a musical piece into a new different one, e.g. remix
- G10H 2210/145: Composing rules, e.g. harmonic or musical rules, for use in automatic composition; Rule generation algorithms therefor
- G10H 2240/085: Mood, i.e. generation, detection or selection of a particular emotional content or atmosphere in a musical piece
- G10H 2250/005: Algorithms for electrophonic musical instruments or musical processing, e.g. for automatic composition or resource allocation
- G10H 2250/215: Transforms, i.e. mathematical transforms into domains appropriate for musical signal processing, coding or compression
- G10H 2250/311: Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation
- G10H: ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Computer-based systems, devices, and methods for generating musical note sequences are described. One or more musical composition(s) stored in digital media include one or more data object(s) that encode notes and/or note sequences. At least one note sequence is processed to form a time-ordered sequence of parallel notes, which is analyzed to determine a k-back probability transition matrix for the at least one note sequence. An attribute, such as a style, of the at least one note sequence is thus encoded and used to generate new note sequences that embody a similar attribute or style. In some implementations, the at least one note sequence may include a concatenated set of note sequences representative of a particular library of musical compositions.

## Claims

### Claim 1

A computer-implemented method of generating a musical note sequence, the method comprising:
determining a first time-ordered sequence of parallel notes for a first musical note sequence;
determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes; and
generating a music sample from the k-back probability transition matrix.

### Claim 2 (depends on 1)

The method of claim 1 wherein generating a music sample from the k-back probability transition matrix includes generating a second time-ordered sequence of parallel notes based at least in part on the first time-ordered sequence of parallel notes.

### Claim 3 (depends on 2)

The method of claim 2 wherein generating a music sample from the k-back probability transition matrix further includes converting the second time-ordered sequence of parallel notes into a second musical note sequence, and wherein converting the second time-ordered sequence of parallel notes into a second musical note sequence includes applying note parameters to each respective note in the second time-ordered sequence of parallel notes, the note parameters selected from a group consisting of: note parameters copied from the first musical note sequence, note parameters copied from a third musical note sequence, and newly generated note parameters.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
encoding a new musical note sequence that includes the music sample.

### Claim 5 (depends on 4)

The method of claim 4 wherein encoding a new musical note sequence that includes the music sample includes encoding a variation of the first musical note sequence with the music sample in place of the first musical note sequence.

### Claim 6 (depends on 1)

The method of claim 1 wherein determining a first time-ordered sequence of parallel notes for a first musical note sequence includes:
grouping all notes in the first musical note sequence into sets, wherein each set is characterized by a respective note start time;
sorting all sets by note start time; and
sorting all notes within each set by note pitch.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
determining an interval representation of the first time-ordered sequence of parallel notes, wherein determining an interval representation of the first time-ordered sequence of parallel notes includes:
for each set:
determining a lowest-pitch note in the set; and
determining a respective internal interval between each respective pair of adjacent notes in the set;
and wherein determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes includes determining a k-back probability transition matrix based at least in part on the interval representation of the first time-ordered sequence of parallel notes.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
determining a respective external interval between each respective pair of lowest-pitch notes in adjacent sets; and
determining a riffled interval representation of the first time-ordered sequence of parallel notes that, for each set, alternates between representing all internal intervals within the set and representing an external interval between the set and a next adjacent set, and wherein determining a k-back probability transition matrix based at least in part on the interval representation of the first time-ordered sequence of parallel notes includes determining a k-back probability transition matrix based at least in part on the riffled interval representation of the first time-ordered sequence of parallel notes.

### Claim 9 (depends on 1)

The method of claim 1 wherein 1≤k<J, where J is a smallest integer for which every sequence of k parallel notes in the first time-ordered sequence of parallel notes is unique.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
establishing a one-to-one correspondence between notes in the first musical note sequence and notes in the music sample generated from the k-back probability transition matrix.

### Claim 11 (depends on 1)

The method of claim 1 wherein determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes includes determining a k-back probability transition matrix based at least in part on at least one of: note sequences, note interval sequences, note start-time sequences, time interval sequences, and/or time duration sequences.

### Claim 12 (depends on 1)

The method of claim 1 wherein determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes includes:
grouping the first time-ordered sequence of parallel notes into a sequence of tuples each having size k; and
determining a probability transition matrix based at least in part on the tuples, wherein a probability of each successor tuple depends on an immediately previous tuple and not on any additional tuple that precedes the immediately previous tuple.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
determining a second time-ordered sequence of parallel notes for a second musical note sequence, wherein determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes includes determining a k-back probability transition matrix based at least in part on both the first time-ordered sequence of parallel notes and the second time-ordered sequence of parallel notes.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
concatenating a set of musical note sequences in series, wherein determining a first time-ordered sequence of parallel notes for a first musical note sequence includes determining the first time-ordered sequence of parallel notes for the concatenated set of musical note sequences.

### Claim 15 (depends on 14)

The method of claim 14 wherein determining a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes includes, for each pair of successive musical compositions in the concatenated set of musical compositions, characterizing a transition between the pair of successive musical compositions in a prescribed way.

### Claim 16 (depends on 14)

The method of claim 14 wherein the set of musical note sequences consists of a plurality of musical note sequences each having a common characteristic selected from a group consisting of: originating from a common musical composition, being respective tracks of a common multi-track musical composition, embodying a common genre, embodying a common style, embodying a common mood, featuring a common instrument, originating from a common composer, originating from a common performing artist, originating from a common band, originating from a common album, originating from a common producer, originating from a common studio, and/or functioning in a common musical role.

### Claim 17

A system for generating a musical note sequence, the system comprising:
at least one processor; and
a non-transitory processor-readable storage medium communicatively coupled to the at least one processor, the non-transitory processor-readable storage medium storing processor-executable instructions and/or data that, when executed by the at least one processor, cause the at least one processor to:
determine a first time-ordered sequence of parallel notes for the first musical note sequence;
determine a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes; and
generate a music sample from the k-back probability transition matrix.

### Claim 18 (depends on 17)

The system of claim 17, further comprising:
processor-executable instructions and/or data that, when executed by the at least one processor, cause the at least one processor to encode, in the non-transitory processor readable storage medium, a new musical note sequence that includes the music sample.

### Claim 19

A computer program product for generating a musical note sequence, the computer program product comprising:
processor-executable instructions and/or data that, when the computer program product is stored in a non-transitory processor-readable storage medium and executed by at least one processor communicatively coupled to the non-transitory processor-readable storage medium, cause the at least one processor to:
determine a first time-ordered sequence of parallel notes for the first musical note sequence;
determine a k-back probability transition matrix based at least in part on the first time-ordered sequence of parallel notes; and
generate a music sample from the k-back probability transition matrix.

### Claim 20 (depends on 19)

The computer program product of claim 19, further comprising:
processor-executable instructions and/or data that, when executed by the at least one processor, cause the at least one processor to encode, in the non-transitory processor readable storage medium, a new musical note sequence that includes the music sample.
