# US 2023/0109066 A1 · Contextual beamforming to improve signal-to-noise ratio sensitive audio input processing efficiency in noisy environments

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

- Number: US 2023/0109066 A1
- Document ID: US20230109066A1
- Status: Published application
- Kind: A1
- Application number: 17/494,512
- Filed: 2021-10-05
- Published: 2023-04-06
- Earliest claimed: 2021-10-05
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Cola Hung Shih; Vivek Viswanathan Iyer
- Web page: https://patentgrep.com/patent/US20230109066A1

## CPC

- G10L 21/0216: characterised by the method used for estimating noise
- G01S 3/807: the desired condition being maintained automatically
- G10L 17/00: Speaker identification or verification techniques
- G10L 21/0264: characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques
- 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)
- H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)}
- H04R 3/04: for correcting frequency response
- H04R 5/04: Circuit arrangements, {e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments (combinations of amplifiers H03F3/68; stereophonic systems H04S)}
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- G10L 2021/02166: {Microphone arrays; Beamforming}
- H04R 2430/21: Direction finding using differential microphone array [DMA]
- H04R 2499/15: Transducers incorporated in visual displaying devices, e.g. televisions, computer displays, laptops
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- 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

An audio processing system includes a microphone array, a speech detection system, and a neural network noise reduction module. The microphone array includes at least two microphones and provides an audio signal from an environment surrounding the microphone array. The speech detection system receives the audio signal, and processes the audio signal to a) detect that a first user is speaking, b) determine a first direction relative to the audio array when the first user is located at a first location within the environment, and c) provide beamforming processing on the audio signal in the first direction, and to provide a processed audio signal based upon the beamforming processing. The neural network noise reduction module reduces noise in the processed audio signal.

## Claims

### Claim 1

An audio processing system, comprising:
a microphone array including at least two microphones and configured to provide an audio signal from an environment surrounding the microphone array;
a speech detection system configured to receive the audio signal, and to process the audio signal to a) detect that a first user is speaking, b) determine a first direction relative to the audio array when the first user is located at a first location within the environment, and c) provide beamforming processing on the audio signal in the first direction, and to provide a processed audio signal based upon the beamforming processing, wherein, in detecting that the first user is speaking, the speech detection system utilizes a voice identification algorithm including at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm; and
a neural network noise reduction module configured to reduce noise in the processed audio signal.

### Claim 2 (depends on 1)

The audio processing system of claim 1, wherein the speech detection system is further configured to determine that the first user has moved form the first location within the environment to a second location within the environment.

### Claim 3 (depends on 2)

The audio processing system of claim 2, wherein the speech detection system is further configured to determine a second direction relative to the audio array when the first user is located at the second location.

### Claim 4 (depends on 3)

The audio processing system of claim 3, wherein the speech detection system is further configured to provide beamforming processing on the audio signal in the second direction.

### Claim 5 (depends on 1)

The audio processing system of claim 1, wherein, prior to detecting that the first user is speaking, the speech detection system is further configured to characterize a first voice of the first user.

### Claim 6 (depends on 5)

The audio processing system of claim 5, wherein detecting that the first user is speaking is based upon the characterization of the first voice.

### Claim 7 (depends on 5)

The audio processing system of claim 5, wherein the speech detection system is further configured to characterize a second voice of a second user.

### Claim 8 (depends on 7)

The audio processing system of claim 7, wherein the speech detection system is further configured to process the audio signal to a) detect that the second user is speaking, b) determine a third direction relative to the audio array when the second user is located at a third location within the environment, and c) provide beamforming processing on the audio signal in the third direction.

### Claim 9

(canceled)

### Claim 10 (depends on 1)

The audio processing system of claim 1, wherein, in determining the first direction, the speech detection system is further configured to determine a time delay in the audio signal between the microphones of the microphone array.

### Claim 11

A method comprising:
providing, by a microphone array of an audio processing system, an audio signal from an environment surrounding the microphone array, wherein the microphone array includes at least two microphones;
characterizing a first voice of a first user and a second voice of a second user;
processing the audio signal to a) detect that the first user is speaking utilizing a speaker diarization model to distinguish the first voice from the second voice, b) determine a first direction relative to the audio array when the first user is located at a first location within the environment, and c) provide beamforming processing on the audio signal in the first direction;
providing a processed audio signal based upon the beamforming processing; and
reducing noise in the processed audio signal.

### Claim 12 (depends on 11)

The method of claim 11, further comprising determining that the first user has moved form the first location within the environment to a second location within the environment.

### Claim 13 (depends on 12)

The method of claim 12, further comprising determining a second direction relative to the audio array when the first user is located at the second location.

### Claim 14 (depends on 13)

The method of claim 13, further comprising providing beamforming processing on the audio signal in the second direction.

### Claim 15

(canceled)

### Claim 16 (depends on 11)

The method of claim 11, wherein detecting that the first user is speaking is based upon the characterization of the first voice.

### Claim 17

(canceled)

### Claim 18 (depends on 11)

The method of claim 11, further comprising processing the audio signal to a) detect that the second user is speaking, b) determine a third direction relative to the audio array when the second user is located at a third location within the environment, and c) provide beamforming processing on the audio signal in the third direction.

### Claim 19 (depends on 11)

The method of claim 11 wherein, in detecting that the first user is speaking, the method further comprises utilizing at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm.

### Claim 20

An information handling system, comprising:
a microphone array including at least two microphones and configured to provide an audio signal from an environment surrounding the microphone array; and
a processor configured to provide an audio processing system including:
a speech detection system configured to receive the audio signal, and to process the audio signal to a) detect that a first user is speaking, b) determine a first direction relative to the audio array when the first user is located at a first location within the environment, and c) provide beamforming processing on the audio signal in the first direction, and to provide a processed audio signal based upon the beamforming processing, wherein, in detecting that the first user is speaking, the speech detection system utilizes a voice identification algorithm including at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm; and
a neural network noise reduction module configured to reduce noise in the processed audio signal.
