# US 2026/0073931 A1 · Systems And Methods Of Jointly Optimized Uplink Downlink Audio Processing

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

- Number: US 2026/0073931 A1
- Document ID: US20260073931A1
- Status: Published application
- Kind: A1
- Application number: 18/883,416
- Filed: 2024-09-12
- Published: 2026-03-12
- Earliest claimed: 2024-08-28
- Assignees: Agora Lab, Inc.
- Applicants: Agora Lab, Inc.
- Inventors: Siqiang Yao; Sen Li; Guangjian Xu; Ruofei Chen
- Web page: https://patentgrep.com/patent/US20260073931A1

## CPC

- G10L 21/0208: Noise filtering
- G10L 21/0232: Processing in the frequency domain
- G10L 25/84: for discriminating voice from noise
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method of processing audio is disclosed. The method includes capturing, via a recording device of an apparatus, an audio signal, wherein the audio signal includes background noise. The method also includes determining, at an uplink stage by a processor, whether the audio signal includes a voice segment of a speaker, and filtering, initially during the uplink stage, the audio signal to suppress or eliminate the background noise. The method further includes determining, by the processor, one or more parameters associated with the audio signal, and responsive to receiving the one or more parameters, filtering, at the downlink stage and based on the one or more parameters, an audio source associated with the audio signal that is played through a playback device of the apparatus during capturing of the audio signal, whereby the audio source includes the background noise of the audio signal captured by the recording device.

## Claims

### Claim 1

A method of processing audio, comprising:
capturing, via a recording device of an apparatus, an audio signal, wherein the audio signal includes background noise;
determining, at an uplink stage by a processor, whether the audio signal includes a voice segment of a speaker;
filtering, initially during the uplink stage, the audio signal to suppress or eliminate the background noise;
determining, by the processor, one or more parameters associated with the audio signal; and
responsive to receiving the one or more parameters, filtering, at a downlink stage and based on the one or more parameters, an audio source associated with the audio signal that is played through a playback device of the apparatus during capturing of the audio signal, wherein the audio source includes the background noise of the audio signal captured by the recording device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the audio source includes music played through the playback device of the apparatus, the voice segment of the speaker is data representing singing of the speaker that is associated with the music, and the filtering of the audio source at the downlink stage modifies the audio source playing through the playback device prior to the recording device capturing the audio source as background noise.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
responsive to filtering the audio signal to suppress or eliminate the background noise, transmitting, in real-time, the audio signal to a receiver.

### Claim 4 (depends on 1)

The method of claim 1, wherein filtering the audio signal to suppress or eliminate the background noise further includes:
responsive to determining that the audio signal includes the voice segment of the speaker, modifying the filtering of the audio signal to suppress or eliminate less of the background noise compared to the initial filtering of the audio signal.

### Claim 5 (depends on 1)

The method of claim 1, wherein filtering the audio signal to suppress or eliminate the background noise further includes:
responsive to determining that the audio signal is free of the voice segment of the speaker, modifying the filtering of the audio signal to suppress or eliminate more of the background noise compared to the initial filtering of the audio signal.

### Claim 6 (depends on 1)

The method of claim 1, wherein the uplink stage includes one or more filtering modules to filter the audio signal to suppress or eliminate the background noise.

### Claim 7 (depends on 6)

The method of claim 6, wherein the one or more filtering modules includes an acoustic echo cancellation (AEC) module and a noise suppression module.

### Claim 8 (depends on 1)

The method of claim 1, wherein the downlink stage includes a perceptual equalizer (PEQ) to filter the audio source that is played through the playback device of the apparatus.

### Claim 9 (depends on 8)

The method of claim 8, wherein responsive to receiving the one or more parameters, filtering, at the downlink stage and based on the one or more parameters, an audio source associated with the audio signal that is played through a playback device of the apparatus during capturing of the audio signal further includes:
modifying one or more filtering parameters of the PEQ based upon the one or more parameters communicated from the uplink stage to the downlink stage.

### Claim 10 (depends on 9)

The method of claim 9, wherein the one or more parameters communicated from the uplink stage to the downlink stage include a signal-to-noise ratio (SNR) and processing capability of the AEC module with respect to one or more frequency bands of the audio source.

### Claim 11

An apparatus for processing audio, comprising:
a non-transitory memory; and
a processor configured to execute instructions stored in the non-transitory memory to:
capture, via a recording device of an apparatus, an audio signal, wherein the audio signal includes background noise;
determine, at an uplink stage by the processor, whether the audio signal includes a voice segment of a speaker;
filter, initially during the uplink stage, the audio signal to suppress or eliminate the background noise;
determine, by the processor, one or more parameters associated with the audio signal; and
responsive to receiving the one or more parameters, filter, at a downlink stage and based on the one or more parameters, an audio source associated with the audio signal that is played through a playback device of the apparatus during capturing of the audio signal, wherein the audio source includes the background noise of the audio signal captured by the recording device.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the processor is further configured to execute instructions stored in the non-transitory memory to:
responsive to filtering the audio signal to suppress or eliminate the background noise, transmit, in real-time, the audio signal to a receiver.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein the processor is further configured to execute instructions stored in the non-transitory memory to:
responsive to determining that the audio signal includes the voice segment of the speaker, modify the filtering of the audio signal to suppress or eliminate less of the background noise compared to the initial filtering of the audio signal.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the processor is further configured to execute instructions stored in the non-transitory memory to:
responsive to determining that the audio signal is free of the voice segment of the speaker, modify the filtering of the audio signal to suppress or eliminate more of the background noise compared to the initial filtering of the audio signal.

### Claim 15 (depends on 11)

The apparatus of claim 11, wherein the uplink stage includes one or more filtering modules to filter the audio signal to suppress or eliminate the background noise; and
wherein the one or more filtering modules includes acoustic echo cancellation (AEC) module and a noise suppression module.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein the downlink stage includes a perceptual equalizer (PEQ) to filter the audio source that is played through the playback device of the apparatus.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein responsive to receiving the one or more parameters, filter, at the downlink stage and based on the one or more parameters, the audio source associated with the audio signal that is played through the playback device of the apparatus during capturing of the audio signal further includes instructions to:
modify one or more filtering parameters of the PEQ based upon the one or more parameters communicated from the uplink stage to the downlink stage.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the one or more parameters communicated from the uplink stage to the downlink stage include a signal-to-noise ratio (SNR) and processing capability of the AEC module with respect to one or more frequency bands of the audio source.

### Claim 19

A non-transitory computer-readable storage medium configured to store computer programs for processing audio, the computer programs comprising instructions executable by a processor to:
capture, via a recording device of an apparatus, an audio signal, wherein the audio signal includes background noise;
determine, at an uplink stage by a processor, whether the audio signal includes a voice segment of a speaker;
filter, initially during the uplink stage, the audio signal to suppress or eliminate the background noise;
determine, by the processor, one or more parameters associated with the audio signal; and
responsive to receiving the one or more parameters, filter, at a downlink stage and based on the one or more parameters, an audio source associated with the audio signal that is played through a playback device of the apparatus during capturing of the audio signal, wherein the audio source includes the background noise of the audio signal captured by the recording device.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the computer programs further comprise instructions executable by the processor to:
responsive to filtering the audio signal to suppress or eliminate the background noise, transmit, in real-time, the audio signal to a receiver, wherein the audio source includes music played through the playback device of the apparatus and the voice segment of the speaker is data representing singing of the speaker that is associated with the music.
