# US 2024/0203444 A1 · Methods and apparatus to determine audio quality

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

- Number: US 2024/0203444 A1
- Document ID: US20240203444A1
- Status: Published application
- Kind: A1
- Application number: 18/592,032
- Filed: 2024-02-29
- Published: 2024-06-20
- Earliest claimed: 2020-10-22
- Assignees: Gracenote, Inc.
- Applicants: Gracenote, Inc.
- Inventors: Markus Kurt Cremer
- Web page: https://patentgrep.com/patent/US20240203444A1

## CPC

- G10L 25/60: for measuring the quality of voice signals
- G06F 16/683: using metadata automatically derived from the content
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G10L 25/18: the extracted parameters being spectral information of each sub-band
- G10L 25/30: using neural networks
- H04R 3/04: for correcting frequency response
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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)

## Abstract

Methods, apparatus, systems and articles of manufacture are disclosed to determine audio quality. Example apparatus disclosed herein include an equalization (EQ) model query generator to generate a query to a neural network, the query including a representation of a sample of an audio signal. Example apparatus disclosed herein also include an EQ analyzer to access a plurality of equalization settings determined by the neural network based on the query; and compare the equalization settings to an equalization threshold to determine if the audio signal is to be removed from subsequent processing.

## Claims

### Claim 1

A tangible, non-transitory computer readable medium comprising instructions, which when executed, cause one or more processors to perform a set of operations comprising:
transforming at least a portion of an audio signal into a simplified representation of the audio signal;
inputting the simplified representation into an equalization neural network;
based on inputting the simplified representation into the equalization neural network, determining equalization settings;
determining whether the equalization settings satisfy an equalization threshold; and
in response to determining that the equalization settings satisfy the equalization threshold, identifying the audio signal as satisfactory audio quality for subsequent processing.

### Claim 2 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the simplified representation comprises a constant-Q transformation of the audio signal.

### Claim 3 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the simplified representation comprises a Fourier transform of the audio signal.

### Claim 4 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio signal comprises music.

### Claim 5 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein determining whether the equalization settings satisfy an equalization threshold is based determining a genre of the audio signal.

### Claim 6 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the neural network comprises a convolutional neural network.

### Claim 7 (depends on 6)

The tangible, non-transitory computer readable medium of claim 6, wherein the set of operations further comprises training the neural network using a library of reference media that correspond with equalization profiles.

### Claim 8 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the set of operations further comprises determining that the equalization settings do not satisfy the equalization threshold and removing the audio signal from subsequent processing.

### Claim 9 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the set of operations further comprises, in response to identifying the audio signal as satisfactory audio quality for subsequent processing, recommending the audio signal for addition to at least one playlist.

### Claim 10 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the set of operations further comprises, in response to identifying the audio signal as satisfactory audio quality for subsequent processing, applying a filter coefficient to the audio signal to determine an audio quality parameter of the audio signal.

### Claim 11

A computer-implemented method comprising:
transforming at least a portion of an audio signal into a simplified representation of the audio signal;
inputting the simplified representation into an equalization neural network;
based on inputting the simplified representation into the equalization neural network, determining equalization settings;
determining whether the equalization settings satisfy an equalization threshold; and
in response to determining that the equalization settings satisfy the equalization threshold, identifying the audio signal as satisfactory audio quality for subsequent processing.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, wherein the simplified representation comprises a constant-Q transformation of the audio signal.

### Claim 13 (depends on 11)

The computer-implemented method of claim 11, wherein the simplified representation comprises a Fourier transform of the audio signal.

### Claim 14 (depends on 11)

The computer-implemented method of claim 11, wherein the audio signal comprises music.

### Claim 15 (depends on 11)

The computer-implemented method of claim 11, wherein determining whether the equalization settings satisfy an equalization threshold is based determining a genre of the audio signal.

### Claim 16 (depends on 11)

The computer-implemented method of claim 11, wherein the neural network comprises a convolutional neural network.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, further comprising training the neural network using a library of reference media that correspond with equalization profiles.

### Claim 18 (depends on 11)

The computer-implemented method of claim 11, further comprising determining that the equalization settings do not satisfy the equalization threshold and removing the audio signal from subsequent processing.

### Claim 19 (depends on 11)

The computer-implemented method of claim 11, further comprising, in response to identifying the audio signal as satisfactory audio quality for subsequent processing, recommending the audio signal for addition to at least one playlist.

### Claim 20

A computing device comprising:
one or more processors; and
a tangible, non-transitory computer readable medium comprising instructions, which when executed, cause the one or more processors to perform a set of operations comprising:
transforming at least a portion of an audio signal into a simplified representation of the audio signal;
inputting the simplified representation into an equalization neural network;
based on inputting the simplified representation into the equalization neural network, determining equalization settings;
determining whether the equalization settings satisfy an equalization threshold; and
in response to determining that the equalization settings satisfy the equalization threshold, identifying the audio signal as satisfactory audio quality for subsequent processing.
