# US 2025/0166650 A1 · Method for reducing voice noise, method for training model, and device

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

- Number: US 2025/0166650 A1
- Document ID: US20250166650A1
- Status: Published application
- Kind: A1
- Application number: 18/880,052
- Filed: 2023-07-12
- Published: 2025-05-22
- Earliest claimed: 2022-07-21
- Assignees: Bigo Technology Pte. Ltd.
- Applicants: Bigo Technology Pte. Ltd.
- Inventors: Shanyi WEI; Liang LIU
- Web page: https://patentgrep.com/patent/US20250166650A1

## CPC

- G10L 21/0208: Noise filtering
- G10L 25/30: using neural networks
- G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10)
- G10L 21/0216: characterised by the method used for estimating noise
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method for reducing voice noise, including: acquiring an algorithm activity detection result corresponding to a current audio frame to be processed by detecting the current audio frame using a predetermined voice activity detection algorithm; acquiring a target activity detection result corresponding to the current audio frame by merging a model activity detection result corresponding to a previous audio frame and the algorithm activity detection result corresponding to the current audio frame, wherein the model activity detection result is outputted by a predetermined voice noise reduction network model; acquiring an initial noise reduction audio frame by performing, based on the target activity detection result, noise estimation and noise elimination on the current audio frame; and outputting a target noise reduction audio frame and a model activity detection result corresponding to the current audio frame by inputting the initial noise reduction audio frame into the predetermined voice noise reduction network model.

## Claims

### Claim 1

A method for reducing voice noise, comprising:
acquiring an algorithm activity detection result corresponding to a current audio frame to be processed by detecting the current audio frame using a predetermined voice activity detection algorithm;
acquiring a target activity detection result corresponding to the current audio frame by merging a model activity detection result corresponding to a previous audio frame and the algorithm activity detection result corresponding to the current audio frame, wherein the model activity detection result is outputted by a predetermined voice noise reduction network model;
acquiring an initial noise reduction audio frame by performing, based on the target activity detection result, noise estimation and noise elimination on the current audio frame; and
outputting a target noise reduction audio frame and a model activity detection result corresponding to the current audio frame by inputting the initial noise reduction audio frame into the predetermined voice noise reduction network model.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the algorithm activity detection result comprises a first probability value of a voice present in a corresponding audio frame, and the model activity detection result comprises a second probability value of a voice present in the corresponding audio frame; and
acquiring the target activity detection result corresponding to the current audio frame by merging the model activity detection result corresponding to the previous audio frame with the algorithm activity detection result corresponding to the current audio frame comprises:
acquiring a third probability value by calculating the second probability value in the model activity detection result corresponding to the previous audio frame and the first probability value in the algorithm activity detection result corresponding to the current audio frame in a predetermined calculation mode, and determining the target activity detection result corresponding to the current audio frame based on the third probability value.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the algorithm activity detection result comprises a fourth probability value of a voice present in each of a predetermined number of frequency points in a corresponding audio frame; and the model activity detection result comprises a fifth probability value of a voice present in each of the predetermined number of frequency points in the corresponding audio frame; and
acquiring the target activity detection result corresponding to the current audio frame by merging the model activity detection result corresponding to the previous audio frame with the algorithm activity detection result corresponding to the current audio frame comprises:
acquiring a sixth probability value, for each of the predetermined number of frequency points, by calculating the fifth probability value of a single frequency point in the model activity detection result corresponding to the previous audio frame and the fourth probability value of the single frequency point in the algorithm activity detection result corresponding to the current audio frame in a predetermined calculation mode; and
determining the target activity detection result corresponding to the current audio frame based on the predetermined number of sixth probability values.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the predetermined calculation mode is one of taking a maximum value, taking a minimum value, calculating an average value, summing, calculating a weighted sum, or calculating a weighted average value.

### Claim 5 (depends on 1)

The method according to claim 1, wherein inputting the initial noise reduction audio frame into the predetermined voice noise reduction network model comprises:
acquiring a target input signal by performing feature extraction with a predetermined feature dimension on the initial noise reduction audio frame; and
inputting the target input signal into the predetermined voice noise reduction network model, or inputting the target input signal and the initial noise reduction audio frame into the predetermined voice noise reduction network model.

### Claim 6

A method for training a model, comprising:
acquiring a sample algorithm activity detection result corresponding to a current sample audio frame by detecting the current sample audio frame using a predetermined voice activity detection algorithm, wherein the current sample audio frame is associated with an activity detection label and a pure audio frame;
acquiring a target sample activity detection result corresponding to the current sample audio frame by merging a sample model activity detection result corresponding to a previous sample audio frame with a sample algorithm activity detection result corresponding to the current sample audio frame, wherein the sample model activity detection result is outputted by a voice noise reduction network model;
acquiring an initial noise reduction sample audio frame by performing, based on the target activity sample detection result, noise estimation and noise elimination on the current sample audio frame;
outputting a target sample noise reduction audio frame and a sample model activity detection result corresponding to the current sample audio frame by inputting the initial noise reduction sample audio frame into the voice noise reduction network model; and
determining a first loss relationship based on the target sample noise reduction audio frame and the pure audio frame, determining a second loss relationship based on the sample model activity detection result and the activity detection label, and training the voice noise reduction network model based on the first loss relationship and the second loss relationship.

### Claim at position 7

7-11. (canceled)

### Claim 12 (depends on 3)

The method according to claim 3, wherein the predetermined calculation mode is one of taking a maximum value, taking a minimum value, calculating an average value, summing, calculating a weighted sum, or calculating a weighted average value.

### Claim 13 (depends on 6)

The method according to claim 6, wherein the sample algorithm activity detection result includes a first sample probability value of a voice present in a corresponding sample audio frame, and the sample model activity detection result includes a second sample probability value of a voice present in the corresponding sample audio frame;
acquiring the target sample activity detection result corresponding to the current sample audio frame by merging the sample model activity detection result corresponding to the previous sample audio frame with the sample algorithm activity detection result corresponding to the current sample audio frame comprises:
acquiring a third sample probability value by calculating the second sample probability value in the sample model activity detection result corresponding to the previous sample audio frame and the first sample probability value in the sample algorithm activity detection result corresponding to the current sample audio frame in a predetermined calculation mode; and
determining the target sample activity detection result corresponding to the current sample audio frame based on the third sample probability value.

### Claim 14 (depends on 6)

The method according to claim 6, wherein the sample algorithm activity detection result includes a fourth sample probability value of a voice present in each of a predetermined number of frequency points in the corresponding audio frame; and the model activity detection result includes a fifth sample probability value of a voice present in each of the predetermined number of frequency points in the corresponding audio frame;
acquiring the target sample activity detection result corresponding to the current sample audio frame by merging the sample model activity detection result corresponding to the previous sample audio frame with the sample algorithm activity detection result corresponding to the current sample audio frame comprises:
acquiring a sixth sample probability value, for each frequency point in the predetermined number of frequency points, by calculating the fifth sample probability value of a single frequency point in the sample model activity detection result corresponding to the previous sample audio frame and the fourth sample probability value of the single frequency point in the sample algorithm activity detection result corresponding to the current sample audio frame in a predetermined calculation mode; and
determining the target sample activity detection result corresponding to the current sample audio frame based on the predetermined number of sixth sample probability values.

### Claim 15 (depends on 6)

The method according to claim 6, wherein inputting the initial noise reduction sample audio frame into the predetermined voice noise reduction network model comprises:
acquiring a target input signal by performing feature extraction with a predetermined feature dimension on the initial noise reduction sample audio frame; and
inputting the target input signal into the predetermined voice noise reduction network model, or inputting the target input signal and the initial noise reduction sample audio frame into the voice noise reduction network model.

### Claim 16

An electrical device for reducing voice noise, comprising:
at least one processor; and
a memory being in communication connection with the at least one processor, wherein
the memory is configured to store a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, causes the at least one processor to perform:
acquiring an algorithm activity detection result corresponding to a current audio frame to be processed by detecting the current audio frame using a predetermined voice activity detection algorithm;
acquiring a target activity detection result corresponding to the current audio frame by merging a model activity detection result corresponding to a previous audio frame and the algorithm activity detection result corresponding to the current audio frame, wherein the model activity detection result is outputted by a predetermined voice noise reduction network model;
acquiring an initial noise reduction audio frame by performing, based on the target activity detection result, noise estimation and noise elimination on the current audio frame; and
outputting a target noise reduction audio frame and a model activity detection result corresponding to the current audio frame by inputting the initial noise reduction audio frame into the predetermined voice noise reduction network model.

### Claim 17 (depends on 16)

The device according to claim 16, wherein the algorithm activity detection result comprises a first probability value of a voice present in a corresponding audio frame, and the model activity detection result comprises a second probability value of a voice present in the corresponding audio frame; and
the computer program, when executed by the at least one processor, causes the at least one processor to perform:
acquiring a third probability value by calculating the second probability value in the model activity detection result corresponding to the previous audio frame and the first probability value in the algorithm activity detection result corresponding to the current audio frame in a predetermined calculation mode, and determining the target activity detection result corresponding to the current audio frame based on the third probability value.

### Claim 18 (depends on 16)

The device according to claim 16, wherein the algorithm activity detection result comprises a fourth probability value of a voice present in each of a predetermined number of frequency points in a corresponding audio frame; and the model activity detection result comprises a fifth probability value of a voice present in each of the predetermined number of frequency points in the corresponding audio frame; and
the computer program, when executed by the at least one processor, causes the at least one processor to perform:
acquiring a sixth probability value, for each of the predetermined number of frequency points, by calculating the fifth probability value of a single frequency point in the model activity detection result corresponding to the previous audio frame and the fourth probability value of the single frequency point in the algorithm activity detection result corresponding to the current audio frame in a predetermined calculation mode; and
determining the target activity detection result corresponding to the current audio frame based on the predetermined number of sixth probability values.

### Claim 19 (depends on 17)

The device according to claim 17, wherein the predetermined calculation mode is one of taking a maximum value, taking a minimum value, calculating an average value, summing, calculating a weighted sum, or calculating a weighted average value.

### Claim 20 (depends on 18)

The device according to claim 18, wherein the predetermined calculation mode is one of taking a maximum value, taking a minimum value, calculating an average value, summing, calculating a weighted sum, or calculating a weighted average value.

### Claim 21 (depends on 16)

The device according to claim 16, wherein the computer program, when executed by the at least one processor, causes the at least one processor to perform:
acquiring a target input signal by performing feature extraction with a predetermined feature dimension on the initial noise reduction audio frame; and
inputting the target input signal into the predetermined voice noise reduction network model, or inputting the target input signal and the initial noise reduction audio frame into the predetermined voice noise reduction network model.

### Claim 22 (depends on 6)

An electrical device for training a model, comprising:
at least one processor; and
a memory being in communication connection with the at least one processor, wherein
the memory is configured to store a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, causes the at least one processor to perform the method for training a model as defined in claim 6.

### Claim 23 (depends on 1)

A non-transitory computer-readable storage medium, configured to store a computer program therein, the computer program, when run by a processor, causes the processor to perform the method for reducing voice noise as defined in claim 1.

### Claim 24 (depends on 6)

A non-transitory computer-readable storage medium, configured to store a computer program therein, the computer program, when run by a processor, causes the processor to perform the method for training a model as defined in claim 6.
