# US 2025/0157451 A1 · Methods and Apparatus for Harmonic Source Enhancement

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

- Number: US 2025/0157451 A1
- Document ID: US20250157451A1
- Status: Published application
- Kind: A1
- Application number: 19/021,910
- Filed: 2025-01-15
- Published: 2025-05-15
- Earliest claimed: 2020-04-16
- Assignees: Gracenote, Inc.
- Applicants: Gracenote, Inc.
- Inventors: Zafar Rafii
- Web page: https://patentgrep.com/patent/US20250157451A1

## CPC

- G10K 11/175: using interference effects; Masking sound
- G06F 3/162: {Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs}
- G10L 25/18: the extracted parameters being spectral information of each sub-band
- G10K: SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Methods and apparatus for harmonic source enhancement are disclosed herein. An example apparatus includes an interface to receive a media signal. The example apparatus also includes a harmonic source enhancer to determine a magnitude spectrogram of audio corresponding to the media signal; generate a time-frequency mask based on the magnitude spectrogram; and apply the time-frequency mask to the magnitude spectrogram to enhance a harmonic source of the media signal.

## Claims

### Claim 1

A tangible, non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform a set of operations comprising:
determining an audio spectrogram corresponding to a media signal;
based on the determined audio spectrogram, enhancing a harmonic source of the media signal;
comparing the enhanced harmonic source media signal with one or more reference media signals to determine an audio characteristic corresponding to the enhanced harmonic source; and
based on the determined audio characteristic, identifying at least one of a song, an advertisement, a show, and a video game.

### Claim 2 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein determining an audio spectrogram comprises transforming audio of the media signal into a time-frequency representation using a Fourier transform.

### Claim 3 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein determining an audio spectrogram comprises transforming audio of the media signal into a time-frequency representation using a Constant Q transform.

### Claim 4 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio spectrogram comprises a magnitude spectrogram.

### Claim 5 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio characteristic comprises an instrument corresponding to the media signal.

### Claim 6 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio characteristic comprises an instrument corresponding to the enhanced harmonic source.

### Claim 7 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio characteristic comprises a genre corresponding to the enhanced harmonic source.

### Claim 8 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the audio characteristic comprises a reference harmonic source that corresponds to the enhanced harmonic source.

### Claim 9 (depends on 1)

The tangible, non-transitory computer readable medium of claim 1, wherein the set of operations further comprise obtaining at least one of a classification or an identifier corresponding to the media signal.

### Claim 10

A computer-implemented method comprising:
determining an audio spectrogram corresponding to a media signal;
based on the determined audio spectrogram, enhancing a harmonic source of the media signal;
comparing the enhanced harmonic source media signal with one or more reference media signals to determine an audio characteristic corresponding to the enhanced harmonic source; and
based on the determined audio characteristic, identifying at least one of a song, an advertisement, a show, and a video game.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein determining an audio spectrogram comprises transforming audio of the media signal into a time-frequency representation using a Fourier transform.

### Claim 12 (depends on 10)

The computer-implemented method of claim 10, wherein determining an audio spectrogram comprises transforming audio of the media signal into a time-frequency representation using a Constant Q transform.

### Claim 13 (depends on 10)

The computer-implemented method of claim 10, wherein the audio spectrogram comprises a magnitude spectrogram.

### Claim 14 (depends on 10)

The computer-implemented method of claim 10, wherein the audio characteristic comprises an instrument corresponding to the media signal.

### Claim 15 (depends on 10)

The computer-implemented method of claim 10, wherein the audio characteristic comprises an instrument corresponding to the enhanced harmonic source.

### Claim 16 (depends on 10)

The computer-implemented method of claim 10, wherein the audio characteristic comprises a genre corresponding to the enhanced harmonic source.

### Claim 17 (depends on 10)

The computer-implemented method of claim 10, wherein the audio characteristic comprises a reference harmonic source that corresponds to the enhanced harmonic source.

### Claim 18 (depends on 10)

The computer-implemented method of claim 10, wherein the set of operations further comprise obtaining at least one of a classification or an identifier corresponding to the media signal.

### Claim 19

A computing device comprising:
one or more processors; and
a tangible, non-transitory computer readable medium comprising instructions that, when executed, cause the one or more processors to perform a set of operations comprising:
determining an audio spectrogram corresponding to a media signal;
based on the determined audio spectrogram, enhancing a harmonic source of the media signal;
comparing the enhanced harmonic source media signal with one or more reference media signals to determine an audio characteristic corresponding to the enhanced harmonic source; and
based on the determined audio characteristic, identifying at least one of a song, an advertisement, a show, and a video game.

### Claim 20 (depends on 19)

The computing device of claim 19, wherein the audio characteristic comprises at least one of: (i) an instrument corresponding to the media signal; (ii) an instrument corresponding to the enhanced harmonic source; and (iii) a genre corresponding to the enhanced harmonic source.
