# US 2026/0263738 A1 · Method, system, and medium for affective music recommendation and composition

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

- Number: US 2026/0263738 A1
- Document ID: US20260263738A1
- Status: Published application
- Kind: A1
- Application number: 19/684,710
- Filed: 2026-05-21
- Published: 2026-09-10
- Earliest claimed: 2020-02-24
- Assignees: Lucid, Inc.
- Applicants: Lucid Inc.
- Inventors: Aaron Labbé
- Web page: https://patentgrep.com/patent/US20260263738A1

## CPC

- A61M 21/02: for inducing sleep or relaxation, e.g. by direct nerve stimulation, hypnosis, analgesia (for massage A61H; electrotherapy A61N, e.g. applying alternating or intermittent electric currents for producing anaesthesia A61N1/36021)
- G10G 1/00: Means for the representation of music
- 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)}
- G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training
- A61M 21/00: Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M 2021/0027: {by the hearing sense}
- A61M 2205/3303: Using a biosensor
- G06F 16/635: Filtering based on additional data, e.g. user or group profiles
- G10H 1/0008: {Associated control or indicating means}
- G10H 2210/111: Automatic composing, i.e. using predefined musical rules
- G10H 2210/125: Medley, i.e. linking parts of different musical pieces in one single piece, e.g. sound collage, DJ mix
- G10H 2220/116: for graphical editing of sound parameters or waveforms, e.g. by graphical interactive control of timbre, partials or envelope
- G10H 2220/371: Vital parameter control, i.e. musical instrument control based on body signals, e.g. brainwaves, pulsation, temperature or perspiration; Biometric information
- G10H 2240/085: Mood, i.e. generation, detection or selection of a particular emotional content or atmosphere in a musical piece
- G10H 2240/131: Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set
- G10H 2250/311: Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation
- A61M: DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY (introducing media into or onto the bodies of animals A61D7/00; means for inserting tampons A61F13/26; devices for administering food or medicines orally A61J; containers for collecting, storing or administering blood or medical fluids A61J1/05); DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY (surgery A61B; chemical aspects of surgical articles A61L); DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR {(Electrotherapy, e.g. producing anaesthesia by the use of alternating or intermittent currents A61N1/36021)}
- G10G: REPRESENTATION OF MUSIC; RECORDING MUSIC IN NOTATION FORM; ACCESSORIES FOR MUSIC OR MUSICAL INSTRUMENTS NOT OTHERWISE PROVIDED FOR, e.g. SUPPORTS (music stands A47B; non-musical aspects of musical toy instruments A63H5/00; metronomes G04F5/02; teaching music G09B15/00)
- 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
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method, system, and medium for affective music recommendation and composition. A listener's current affective state and target affective state are identified, and an audio stream, such as a music playlist, is generated with the intent of effecting a controlled trajectory of the listener's affective state from the current state to the target state. The audio stream is generated by a machine learning system trained using data from the listener and/or other users indicating the effectiveness of specific audio segments, or audio segments having specific features, in effecting the desired affective trajectory. The audio stream is presented to the user as an auditory stimulus. The machine learning system may be updated based on the affective state changes induced in the listener after exposure to the auditory stimulus. The machine learning system may also be used to compose, master, and/or adapt music configured to induce specific affective responses in listeners.

## Claims

### Claim 1

A processor-executed method for selecting music for a listener, comprising:
maintaining a personalized audio segment identification machine learning model specific to a listener, the personalized audio segment identification machine learning model having been trained at least in part using training data comprising:
audio feature data of a plurality of training audio segments presented to the listener; and
affective response data obtained from the listener in association with presentation of the plurality of training audio segments;
providing as input to the personalized audio segment identification machine learning model a target affective state of the listener;
using the personalized audio segment identification machine learning model to select a first audio segment from a plurality of audio segments, based on the target affective state of the listener, for inclusion in an audio stream, the plurality of training audio segments not including the first audio segment; and
causing the audio stream to be presented to the listener via at least one speaker of a listener device.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the affective response data obtained from the listener comprises self-evaluation data received from the listener via the listener device.

### Claim 3 (depends on 2)

The method of claim 2, wherein:
the self-evaluation data comprises an indication of one or more of:
a valence value, an activation value, a named affective state, or a level of an affective dimension.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
the affective response data obtained from the listener comprises sensor data received from one or more sensors associated with the listener.

### Claim 5 (depends on 4)

The method of claim 4, wherein:
the one or more sensors comprise one or more of:
a physiological sensor, a biometric sensor, a galvanic skin response sensor, a heart rate sensor, an electroencephalogram sensor, a respiration sensor, a camera, or a microphone.

### Claim 6 (depends on 4)

The method of claim 4, wherein:
the sensor data comprises one or more of:
physiological data correlated with one or more physiological states of the listener, facial expression data, behavioral data, or voice data.

### Claim 7 (depends on 1)

The method of claim 1, wherein:
the selection of the first audio segment for inclusion in the audio stream by the personalized audio segment identification machine learning model comprises:
generating, by the personalized audio segment identification machine learning model, a set of audio feature values predicted to be likely to induce the target affective state in the listener;
comparing the set of audio feature values to audio feature data of each audio segment of the plurality of audio segments; and
based on the comparison, selecting the first audio segment.

### Claim 8 (depends on 7)

The method of claim 7, wherein:
the audio feature data comprises music information retrieval (MIR) data.

### Claim 9 (depends on 8)

The method of claim 8, wherein:
the MIR data comprises global MIR features of the audio segment and time-series MIR features corresponding to a plurality of sub-segments of the audio segment.

### Claim 10 (depends on 7)

The method of claim 7, further comprising:
identifying a current affective state of the listener;
identifying the target affective state of the listener; and
identifying an affective trajectory from the current affective state to the target affective state;
wherein the audio feature values are predicted to be likely to induce at least an initial portion of the affective trajectory.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
identifying an updated affective state of the listener after presentation of the first audio segment;
identifying an updated affective trajectory from the updated affective state to the target affective state;
using the personalized audio segment identification machine learning model to generate a second set of audio feature values predicted to be likely to induce in the listener at least an initial portion of the updated affective trajectory; and
selecting a second audio segment for inclusion in the audio stream based at least in part on the second set of audio feature values.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
identifying the updated affective state comprises receiving updated affective response data obtained from the listener after presentation of the first audio segment.

### Claim 13 (depends on 12)

The method of claim 12, wherein:
the updated affective response data is obtained from the listener via one or more sensors during or after presentation of the first audio segment.

### Claim 14 (depends on 12)

The method of claim 12, wherein:
the updated affective response data comprises self-evaluation data received from the listener via the listener device.

### Claim 15 (depends on 11)

The method of claim 11, wherein:
identifying the updated affective state comprises using a trained affective inference machine learning model to predict the updated affective state based on the current affective state and the audio feature data of the first audio segment.

### Claim 16 (depends on 1)

The method of claim 1, wherein:
the personalized audio segment identification machine learning model comprises a recurrent neural network.

### Claim 17 (depends on 1)

The method of claim 1, further comprising:
after presentation of the first audio segment, receiving updated affective response data obtained from the listener; and
further training the personalized audio segment identification machine learning model using runtime training data comprising the audio feature data of the first audio segment and the updated affective response data.

### Claim 18 (depends on 1)

The method of claim 1, wherein:
the personalized audio segment identification machine learning model is initially trained using transfer learning from a generalist audio segment identification machine learning model trained using affective response data obtained from a population of users other than the listener; and
the first audio segment is selected at least in part based on the training of the personalized audio segment identification machine learning model using the affective response data obtained from the listener.

### Claim 19

A system comprising:
a processor system; and
a memory system having stored thereon:
a personalized audio segment identification machine learning model specific to a listener, the personalized audio segment identification machine learning model having been trained at least in part using training data comprising:
audio feature data of a plurality of training audio segments presented to the listener; and
affective response data obtained from the listener in association with presentation of the plurality of training audio segments; and
instructions executable by the processor system to cause the system to perform operations comprising:
providing as input to the personalized audio segment identification machine learning model a target affective state of the listener;
using the personalized audio segment identification machine learning model to select a first audio segment from a plurality of audio segments, based on the target affective state of the listener, for inclusion in an audio stream, the plurality of training audio segments not including the first audio segment; and
causing the audio stream to be presented to the listener via at least one speaker of a listener device.

### Claim 20

A non-transitory processor-readable medium containing:
a personalized audio segment identification machine learning model specific to a listener, the personalized audio segment identification machine learning model having been trained at least in part using training data comprising:
audio feature data of a plurality of training audio segments presented to the listener; and
affective response data obtained from the listener in association with presentation of the plurality of training audio segments; and
instructions executable by a processor system to cause the processor system to perform operations comprising:
providing as input to the personalized audio segment identification machine learning model a target affective state of the listener;
using the personalized audio segment identification machine learning model to select a first audio segment from a plurality of audio segments, based on the target affective state of the listener, for inclusion in an audio stream, the plurality of training audio segments not including the first audio segment; and
causing the audio stream to be presented to the listener via at least one speaker of a listener device.
