# US 2026/0292422 A1 · Predictive model of sound quality in televisions

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

- Number: US 2026/0292422 A1
- Document ID: US20260292422A1
- Status: Published application
- Kind: A1
- Application number: 19/084,020
- Filed: 2025-03-19
- Published: 2026-09-24
- Earliest claimed: 2025-03-19
- Assignees: Roku, Inc.
- Applicants: Roku, Inc.
- Inventors: Kasper Andersen; Frederik Stauenberg Lindbjerg Halkjær
- Web page: https://patentgrep.com/patent/US20260292422A1

## CPC

- H04R 29/001: {for loudspeakers (H04R29/007 takes precedence)}
- G01R 19/0084: {Measuring voltage only}
- H04R 3/04: for correcting frequency response
- H04S 7/301: {Automatic calibration of stereophonic sound system, e.g. with test microphone}
- G06N 20/00: Machine learning
- H04R 2499/15: Transducers incorporated in visual displaying devices, e.g. televisions, computer displays, laptops
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- H04S: STEREOPHONIC SYSTEMS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Television sound quality has a poor reputation, sometimes due to the designs getting thinner. Common issues include distortion, clipping, muddy dialogue, and lack of bass. Some issues are due to or made worse by errors in tuning. The errors may come from improper measurements, lack of understanding, and prioritization of incorrect metrics. To address this issue, a data driven and objective predictive model is implemented to offer a consistent and scalable way to determine perceived sound quality of a wide range of audio systems. The predictive model can be used to determine optimal tuning parameters that would yield the best perceived sound quality of the audio system.

## Claims

### Claim 1

A method for predicting sound quality, comprising:
acquiring a spherical sound pressure level measurement of an audio system;
extracting one or more objective measurements from the spherical sound pressure level measurement, the one or more objective measurements comprising a spatial variance measurement; and
inputting the one or more objective measurements into a predictive model to obtain a sound quality score of the audio system.

### Claim 2 (depends on 1)

The method of claim 1, further comprising acquiring a voltage measurement of a speaker clamp of the audio system.

### Claim 3 (depends on 2)

The method of claim 2, wherein the spherical sound pressure level measurement is divided by the voltage measurement.

### Claim 4 (depends on 1)

The method of claim 1, wherein the spatial variance measurement quantifies variations of sound pressure level across frequency and space.

### Claim 5 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a direct sound balance measurement.

### Claim 6 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a direct sound quality measurement quantifying a flatness or an amount of errors in a frequency response of direct sound.

### Claim 7 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a power balance measurement over both direct sound and indirect sound.

### Claim 8 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a power quality measurement quantifying a flatness or an amount of errors in a frequency response of both direct sound and indirect sound.

### Claim 9 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a forward directivity measurement quantifying a frequency-dependent ratio between direct sound and indirect sound.

### Claim 10 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise an intermodulation distortion score.

### Claim 11 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a volume displacement measurement quantifying how loud the audio system can produce an audio output and maintain a level of performance.

### Claim 12 (depends on 1)

The method of claim 1, wherein the one or more objective measurements comprise a low frequency extension measurement quantifying a lowest frequency the audio system can produce an audio output.

### Claim 13 (depends on 1)

The method of claim 1, wherein the predictive model comprises a multivariate linear regression model.

### Claim 14 (depends on 1)

The method of claim 1, wherein the predictive model comprises a machine learning model.

### Claim 15 (depends on 1)

The method of claim 1, wherein the audio system is integrated in a television.

### Claim 16

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to:
acquire a spherical sound pressure level measurement of an audio system;
extract one or more objective measurements from the spherical sound pressure level measurement, the one or more objective measurements comprising a spatial variance measurement; and
input the one or more objective measurements into a predictive model to obtain a sound quality score of the audio system.

### Claim 17 (depends on 16)

The one or more non-transitory computer-readable media of claim 16, wherein the instructions further cause the one or more processors to acquire a voltage measurement of a speaker clamp of the audio system, and the spherical sound pressure level measurement is divided by the voltage measurement.

### Claim 18

An apparatus, comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to:
acquire a spherical sound pressure level measurement of an audio system;
extract one or more objective measurements from the spherical sound pressure level measurement, the one or more objective measurements comprising a spatial variance measurement; and
input the one or more objective measurements into a predictive model to obtain a sound quality score of the audio system.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein the one or more objective measurements comprise one or more of: a direct sound balance measurement, a direct sound quality measurement quantifying a flatness or an amount of errors in a frequency response of direct sound, a power balance measurement over both direct sound and indirect sound, a power quality measurement quantifying a flatness or an amount of errors in a frequency response of both direct sound and indirect sound, a forward directivity measurement quantifying a frequency-dependent ratio between direct sound and indirect sound.

### Claim 20 (depends on 18)

The apparatus of claim 18, wherein the one or more objective measurements comprise one or more of: an intermodulation distortion score, a volume displacement measurement quantifying how loud the audio system can produce an audio output and maintain a level of performance, and a low frequency extension measurement quantifying a lowest frequency the audio system can produce an audio output.
