# US 2023/0412998 A1 · Determining and adapting to changes in microphone performance of playback devices

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

- Number: US 2023/0412998 A1
- Document ID: US20230412998A1
- Status: Published application
- Kind: A1
- Application number: 18/461,409
- Filed: 2023-09-05
- Published: 2023-12-21
- Earliest claimed: 2018-05-25
- Assignees: Sonos, Inc.
- Applicants: Sonos, Inc.
- Inventors: Kurt Thomas Soto; Connor Kristopher Smith; Roberto Maria Dizon; Patrick Kevin McPherson; Charles Conor Sleith
- Web page: https://patentgrep.com/patent/US20230412998A1

## CPC

- H04R 29/005: {Microphone arrays}
- G10L 15/08: Speech classification or search
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- H04R 1/406: {microphones}
- 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
- G10L 2015/088: {Word spotting}
- H04R 2227/005: Audio distribution systems for home, i.e. multi-room use
- H04R 2420/07: Applications of wireless loudspeakers or wireless microphones
- 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)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Systems and methods for determining and adapting to changes in microphone performance of playback devices are disclosed herein. In one example, an audio input is received at an array of individual microphones of a network microphone device. Output microphone signals are generated from each of the individual microphones based on the audio input. The output microphone signals are analyzed to detect a trigger event. After detecting the trigger event, the output microphone signals are compared to detect aberrant behavior of one or more of the microphones. Optionally, corrective actions can be taken or suggested based on the detection of aberrant behavior of one or more microphones.

## Claims

### Claim 1

A network microphone device (NMD) comprising:
a plurality of microphones;
one or more processors; and
a computer-readable medium storing instructions that, when executed by the one or more processors, cause the NMD to perform a method comprising:
capturing first sound data via a first set of microphones selected from the plurality of microphones;
processing the first sound data to determine a first intent;
performing a first action based on the determined first intent;
receiving an instruction to disable a particular one or more microphones of the plurality of microphones;
capturing second sound data using a second set of microphones selected from the plurality of microphones, wherein the second set excludes the particular one or more microphones;
processing the second sound data to determine a second intent; and
performing a second action based on the determined second intent.

### Claim 2 (depends on 1)

The NMD of claim 1, wherein processing at least one of the first sound data or the second sound data comprises:
transmitting a voice utterance via a network interface of the NMD to one or more remote computing devices associated with a voice assistant service (VAS); and
receiving, via the network interface, a response from the VAS indicating an intent.

### Claim 3 (depends on 1)

The NMD of claim 1, the method further comprising:
after capturing first sound data, obtaining metadata based on the first sound data;
transmitting the metadata to a remote evaluator; and
receiving an instruction from the remote evaluator to disable the particular one or more microphones.

### Claim 4 (depends on 1)

The NMD of claim 1, wherein the instruction to disable the particular one or more microphones is based on detection of aberrant behavior of the particular one or more microphones.

### Claim 5 (depends on 4)

The NMD of claim 4, wherein the detection of aberrant behavior comprises detection of excess noise.

### Claim 6 (depends on 1)

The NMD of claim 1, wherein processing at least one of the first sound data or the second sound data comprises utilizing a spatial processor.

### Claim 7 (depends on 1)

The NMD of claim 1, wherein performing at least one of the first action or second action comprises modifying a beamforming algorithm of the NMD.

### Claim 8

A method to be performed by a network microphone device (NMD) comprising a plurality of microphones configured to detect sound, the method comprising:
capturing first sound data via a first set of microphones selected from the plurality of microphones;
processing the first sound data to determine a first intent;
performing a first action based on the determined first intent;
receiving an instruction to disable a particular one or more microphones of the plurality of microphones;
capturing second sound data using a second set of microphones selected from the plurality of microphones, wherein the second set excludes the particular one or more microphones;
processing the second sound data to determine a second intent; and
performing a second action based on the determined second intent.

### Claim 9 (depends on 8)

The method of claim 8, wherein processing at least one of the first sound data or the second sound data comprises:
transmitting a voice utterance via a network interface of the NMD to one or more remote computing devices associated with a voice assistant service (VAS); and
receiving, via the network interface, a response from the VAS indicating an intent.

### Claim 10 (depends on 8)

The method of claim 8, further comprising:
after capturing first sound data, obtaining metadata based on the first sound data;
transmitting the metadata to a remote evaluator; and
receiving an instruction from the remote evaluator to disable the particular one or more microphones.

### Claim 11 (depends on 8)

The method of claim 8, wherein the instruction to disable the particular one or more microphones is based on detection of aberrant behavior of the particular one or more microphones.

### Claim 12 (depends on 11)

The method of claim 11, wherein the detection of aberrant behavior comprises detection of excess noise.

### Claim 13 (depends on 8)

The method of claim 8, wherein processing at least one of the first sound data or the second sound data comprises utilizing a spatial processor.

### Claim 14 (depends on 8)

The method of claim 8, wherein performing at least one of the first action or second action comprises modifying a beamforming algorithm of the NMD.

### Claim 15

A tangible, non-transitory, computer-readable medium having stored therein instructions executable by one or more processors to cause a network microphone device (NMD) having a plurality of microphones to perform a method comprising:
capturing first sound data via a first set of microphones selected from the plurality of microphones;
processing the first sound data to determine a first intent;
performing a first action based on the determined first intent;
receiving an instruction to disable a particular one or more microphones of the plurality of microphones;
capturing second sound data using a second set of microphones selected from the plurality of microphones, wherein the second set excludes the particular one or more microphones;
processing the second sound data to determine a second intent; and
performing a second action based on the determined second intent.

### Claim 16 (depends on 15)

The computer-readable medium of claim 15, wherein processing at least one of the first sound data or the second sound data comprises:
transmitting a voice utterance via a network interface of the NMD to one or more remote computing devices associated with a voice assistant service (VAS); and
receiving, via the network interface, a response from the VAS indicating an intent.

### Claim 17 (depends on 15)

The computer-readable medium of claim 15, the method further comprising:
after capturing first sound data, obtaining metadata based on the first sound data;
transmitting the metadata to a remote evaluator; and
receiving an instruction from the remote evaluator to disable the particular one or more microphones.

### Claim 18 (depends on 15)

The computer-readable medium of claim 15, wherein the instruction to disable the particular one or more microphones is based on detection of aberrant behavior of the particular one or more microphones.

### Claim 19 (depends on 15)

The computer-readable medium of claim 15, wherein processing at least one of the first sound data or the second sound data comprises utilizing a spatial processor.

### Claim 20 (depends on 15)

The computer-readable medium of claim 15, wherein performing at least one of the first action or the second action comprises modifying a beamforming algorithm of the NMD.
