# US 2026/0084057 A1 · Systems and methods for modifying a sound based on user preferences

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

- Number: US 2026/0084057 A1
- Document ID: US20260084057A1
- Status: Published application
- Kind: A1
- Application number: 18/893,762
- Filed: 2024-09-23
- Published: 2026-03-26
- Earliest claimed: 2024-09-23
- Assignees: Sony Interactive Entertainment Inc.
- Applicants: Sony Interactive Entertainment Inc.
- Inventors: Victoria Dorn; Andres Aceves
- Web page: https://patentgrep.com/patent/US20260084057A1

## CPC

- A63F 13/54: involving acoustic signals, e.g. for simulating revolutions per minute [RPM] dependent engine sounds in a driving game or reverberation against a virtual wall
- A63F 13/213: comprising photodetecting means, e.g. cameras, photodiodes or infrared cells (A63F13/219 takes precedence)
- A63F 13/215: comprising means for detecting acoustic signals, e.g. using a microphone
- A63F 13/67: adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
- A63F 13/79: involving player-related data, e.g. identities, accounts, preferences or play histories
- G06V 40/174: {Facial expression recognition}
- A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and methods for modifying a sound based on user preferences are described. One of the methods includes receiving first audio data of a first sound to be output from a first virtual object during a play of a game by a user. The method also includes determining, by an artificial intelligence (AI) model, that the first sound is not preferred to be heard by the user and providing an indication to a game engine that the first sound is not preferred to be heard from the user. The method includes modifying, by the game engine, the first audio data with second audio data to be output as a second sound to be heard by the user.

## Claims

### Claim 1

A method for modifying a sound based on user preferences, comprising:
receiving first audio data of a first sound to be output from a first virtual object during a play of a game by a user;
determining, by an artificial intelligence (AI) model, that the first sound is not preferred to be heard by the user;
providing an indication to a game engine that the first sound is not preferred to be heard from the user; and
modifying, by the game engine, the first audio data with second audio data to be output as a second sound preferred to be heard by the user.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
determining whether a permission to modify the first audio data exists, wherein said modifying the first audio data occurs in response to determining that the permission exists.

### Claim 3 (depends on 1)

The method of claim 1, further comprising sending the second audio data instead of the first audio data via a computer network to a client device for outputting the second sound.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
receiving, by the AI model, game context data of the game, wherein the game context data identifies the first virtual object and a second virtual object, the first audio data of the first sound output from the first virtual object, and second audio data of a third sound output from the second virtual object;
receiving, by the AI model, controller input data, wherein the controller input data identifies a first set of one or more buttons selected on one or more game controllers or one or more movements of a second set of one or more buttons selected on the one or more game controllers or a combination thereof;
receiving, by the AI model, audio information generated from a voice of the user;
receiving, by the AI model, textual data from one or more user accounts assigned to the user and an additional user;
receiving, by the AI model, image data identifying a body expression from the user and an additional body expression from the additional user; and
receiving, by the AI model, parameter setting data identifying one or more levels of one or more parameters of one or more sounds to be output by the first virtual object and the second virtual object.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
identifying, from the game context data by the AI model, the first virtual object and the second virtual object and the first audio data of the first sound output from the first virtual object and the second audio data of the third sound output from the second virtual object;
identifying, from the controller input data by the AI model, the first set of one or more buttons selected on the one or more game controllers or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof;
identifying, from the audio information by the AI model, an emotion of the user towards the first sound and an additional emotion of the additional user towards the first sound or the third sound output from the second virtual object;
identifying, from the textual data by the AI model, a liking of the user towards the first sound and an additional liking of the additional user towards the first sound or the third sound;
identifying, from the image data by the AI model, the body expression of the user towards the first sound and the additional body expression of the additional user towards the first sound or the third sound; and
identifying, from the parameter setting data by the AI model, a level of a parameter of the first sound and an additional level of the parameter of the third sound.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
classifying, by the AI model, the first sound as scary or less scary and the third sound as scary or less scary;
classifying, by the AI model, a first preference of the user towards the first sound based on the selection of the first set of one or more buttons or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof, wherein the first preference of the user is classified to output a first classification signal;
classifying, by the AI model, a second preference of the user towards the first sound based on the emotion of the user towards the first sound or the additional emotion of the additional user towards the first sound or the third sound output from the second virtual object, wherein the second preference of the user is classified to output a second classification signal;
classifying, by the AI model, a third preference of the user towards the first sound based on the liking of the user towards the first sound or the additional liking of the additional user towards the first sound or the third sound, wherein the third preference of the user is classified to output a third classification signal;
classifying, by the AI model, a fourth preference of the user towards the first sound based on the body expression of the user towards the first sound or the additional body expression of the additional user towards the first sound or the third sound, wherein the fourth preference of the user is classified to output a fourth classification signal; and
classifying, by the AI model, a fifth preference of the user towards the first sound based on the level of the parameter of the first sound and the additional level of the parameter of the third sound, wherein the fifth preference of the user is classified to output a fifth classification signal.

### Claim 7 (depends on 6)

The method of claim 6, further comprising training the AI model based on the first classification signal, the second classification signal, the third classification signal, the fourth classification signal, and the fifth classification signal.

### Claim 8

A server system for modifying a sound based on user preferences, comprising:
a processor configured to:
receive first audio data of a first sound to be output from a first virtual object during a play of a game by a user;
determine, using an artificial intelligence (AI) model, that the first sound is not preferred to be heard by the user;
provide an indication to a game engine that the first sound is not preferred to be heard from the user; and
modify, using the game engine, the first audio data with second audio data to be output as a second sound preferred to be heard by the user; and
a memory device coupled to the processor.

### Claim 9 (depends on 8)

The server system of claim 8, wherein the processor is configured to:
determine whether a permission to modify the first audio data exists, wherein the first audio data is modified in response to determining that the permission exists.

### Claim 10 (depends on 8)

The server system of claim 8, wherein the processor is configured to send the second audio data instead of the first audio data via a computer network to a client device for outputting the second sound.

### Claim 11 (depends on 8)

The server system of claim 8, wherein the processor is configured to:
receive, using the AI model, game context data of the game, wherein the game context data identifies the first virtual object and a second virtual object, the first audio data of the first sound output from the first virtual object, and second audio data of a third sound output from the second virtual object;
receive, using the AI model, controller input data, wherein the controller input data identifies a first set of one or more buttons selected on one or more game controllers or one or more movements of a second set of one or more buttons selected on the one or more game controllers or a combination thereof;
receive, using the AI model, audio information generated from a voice of the user;
receive, using the AI model, textual data from one or more user accounts assigned to the user and an additional user;
receive, using the AI model, image data identifying a body expression from the user and an additional body expression from the additional user; and
receive, using the AI model, parameter setting data identifying one or more levels of one or more parameters of one or more sounds to be output by the first virtual object and the second virtual object.

### Claim 12 (depends on 11)

The server system of claim 11, wherein the processor is configured to:
identify, from the game context data, the first virtual object and the second virtual object and the first audio data of the first sound output from the first virtual object and the second audio data of the third sound output from the second virtual object, wherein the first and second virtual objects and the first and second audio data are identified using the AI model;
identify, from the controller input data, the first set of one or more buttons selected on the one or more game controllers or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof, wherein the first set of one or more buttons, the one or more movements, or the combination thereof are identified using the AI model;
identify, from the audio information, an emotion of the user towards the first sound and an additional emotion of the additional user towards the first sound or the third sound output from the second virtual object, wherein the emotion and the additional emotion are identified using the AI model;
identify, from the textual data, a liking of the user towards the first sound and an additional liking of the additional user towards the first sound or the third sound, wherein the liking and the additional liking are identified using the AI model;
identify, from the image data by the AI model, the body expression of the user towards the first sound and the additional body expression of the additional user towards the first sound or the third sound, wherein the body expression and the additional body expression are identified using the AI model; and
identify, from the parameter setting data, a level of a parameter of the first sound and an additional level of the parameter of the third sound, wherein the level and the additional level are identified using the AI model.

### Claim 13 (depends on 12)

The server system of claim 12, wherein the processor is configured to:
classify, using the AI model, the first sound as scary or less scary and the third sound as scary or less scary;
classify, using the AI model, a first preference of the user towards the first sound based on the selection of the first set of one or more buttons or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof, wherein the first preference of the user is classified to output a first classification signal;
classify, using the AI model, a second preference of the user towards the first sound based on the emotion of the user towards the first sound or the additional emotion of the additional user towards the first sound or the third sound output from the second virtual object, wherein the second preference of the user is classified to output a second classification signal;
classify, using the AI model, a third preference of the user towards the first sound based on the liking of the user towards the first sound or the additional liking of the additional user towards the first sound or the third sound, wherein the third preference of the user is classified to output a third classification signal;
classify, using the AI model, a fourth preference of the user towards the first sound based on the body expression of the user towards the first sound or the additional body expression of the additional user towards the first sound or the third sound, wherein the fourth preference of the user is classified to output a fourth classification signal; and
classify, using the AI model, a fifth preference of the user towards the first sound based on the level of the parameter of the first sound and the additional level of the parameter of the third sound, wherein the fifth preference of the user is classified to output a fifth classification signal.

### Claim 14 (depends on 13)

The server system of claim 13, wherein the processor is configured to train the AI model based on the first classification signal, the second classification signal, the third classification signal, the fourth classification signal, and the fifth classification signal.

### Claim 15

A non-transitory computer-readable medium that stores instructions for modifying a sound based on user preferences, the instructions when executed by a computer cause the computer to:
receive first audio data of a first sound to be output from a first virtual object during a play of a game by a user;
determine, using an artificial intelligence (AI) model, that the first sound is not preferred to be heard by the user;
provide an indication to a game engine that the first sound is not preferred to be heard from the user; and
modify, using the game engine, the first audio data with second audio data to be output as a second sound preferred to be heard by the user.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions when executed cause the computer to:
determine whether a permission to modify the first audio data exists, wherein said modifying the first audio data occurs in response to determining that the permission exists.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions when executed cause the computer to send the second audio data instead of the first audio data via a computer network to a client device for outputting the second sound.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions when executed cause the computer to:
receive, using the AI model, game context data of the game, wherein the game context data identifies the first virtual object and a second virtual object, the first audio data of the first sound output from the first virtual object, and second audio data of a third sound output from the second virtual object;
receive, using the AI model, controller input data, wherein the controller input data identifies a first set of one or more buttons selected on one or more game controllers or one or more movements of a second set of one or more buttons selected on the one or more game controllers or a combination thereof;
receive, using the AI model, audio information generated from a voice of the user;
receive, using the AI model, textual data from one or more user accounts assigned to the user and an additional user;
receive, using the AI model, image data identifying a body expression from the user and an additional body expression from the additional user; and
receive, using the AI model, parameter setting data identifying one or more levels of one or more parameters of one or more sounds to be output by the first virtual object and the second virtual object.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the instructions when executed cause the computer to:
identify, from the game context data, the first virtual object and the second virtual object and the first audio data of the first sound output from the first virtual object and the second audio data of the third sound output from the second virtual object, wherein the first and second virtual objects and the first and second audio data are identified using the AI model;
identify, from the controller input data, the first set of one or more buttons selected on the one or more game controllers or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof, wherein the first set of one or more buttons, the one or more movements, or the combination thereof are identified using the AI model;
identify, from the audio information, an emotion of the user towards the first sound and an additional emotion of the additional user towards the first sound or the third sound output from the second virtual object, wherein the emotion and the additional emotion are identified using the AI model;
identify, from the textual data, a liking of the user towards the first sound and an additional liking of the additional user towards the first sound or the third sound, wherein the liking and the additional liking are identified using the AI model;
identify, from the image data by the AI model, the body expression of the user towards the first sound and the additional body expression of the additional user towards the first sound or the third sound, wherein the body expression and the additional body expression are identified using the AI model; and
identify, from the parameter setting data, a level of a parameter of the first sound and an additional level of the parameter of the third sound, wherein the level and the additional level are identified using the AI model.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the instructions when executed cause the computer to:
classify, using the AI model, the first sound as scary or less scary and the third sound as scary or less scary;
classify, using the AI model, a first preference of the user towards the first sound based on the selection of the first set of one or more buttons or the one or more movements of the second set of one or more buttons selected on the one or more game controllers or the combination thereof, wherein the first preference of the user is classified to output a first classification signal;
classify, using the AI model, a second preference of the user towards the first sound based on the emotion of the user towards the first sound or the additional emotion of the additional user towards the first sound or the third sound output from the second virtual object, wherein the second preference of the user is classified to output a second classification signal;
classify, using the AI model, a third preference of the user towards the first sound based on the liking of the user towards the first sound or the additional liking of the additional user towards the first sound or the third sound, wherein the third preference of the user is classified to output a third classification signal;
classify, using the AI model, a fourth preference of the user towards the first sound based on the body expression of the user towards the first sound or the additional body expression of the additional user towards the first sound or the third sound, wherein the fourth preference of the user is classified to output a fourth classification signal; and
classify, using the AI model, a fifth preference of the user towards the first sound based on the level of the parameter of the first sound and the additional level of the parameter of the third sound, wherein the fifth preference of the user is classified to output a fifth classification signal; and
train the AI model based on the first classification signal, the second classification signal, the third classification signal, the fourth classification signal, and the fifth classification signal.
