# US 2022/0020387 A1 · Interrupt for noise-cancelling audio devices

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

- Number: US 2022/0020387 A1
- Document ID: US20220020387A1
- Status: Published application
- Kind: A1
- Application number: 17/378,634
- Filed: 2021-07-16
- Published: 2022-01-20
- Earliest claimed: 2020-07-17
- Assignees: Apple Inc.
- Applicants: Apple Inc.
- Inventors: Baptiste P. PAQUIER; Aram M. LINDAHL; Adam E. KRIEGEL; Kisun YOU; Sarang S. RANADE
- Web page: https://patentgrep.com/patent/US20220020387A1

## CPC

- G10K 11/17837: {by retaining part of the ambient acoustic environment, e.g. speech or alarm signals that the user needs to hear}
- G10L 21/0208: Noise filtering
- G06N 20/00: Machine learning
- G10K 11/17885: {additionally using a desired external signal, e.g. pass-through audio such as music or speech}
- G10L 15/08: Speech classification or search
- G10L 17/02: Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
- G10K 2210/108: Communication systems, e.g. where useful sound is kept and noise is cancelled
- G10K 2210/3038: Neural networks
- G10L 17/00: Speaker identification or verification techniques
- G10L 2015/088: {Word spotting}
- 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
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Implementations of the subject technology provide systems and methods for determining whether to interrupt a user of an audio device that is operating in a noise-cancelling mode of operation. For example, the user may desire to be interrupted by one or more pre-designated contacts that are identified at an associated electronic device as interrupt-authorized contacts, or by a person who speaks a designated keyword to the user.

## Claims

### Claim 1

A device of a first user, the device comprising:
secure memory storing a plurality of contacts including contacts designated at the device as interrupt-authorized contacts for a peripheral device; and
one or more processors configured to:
provide audio content to the peripheral device, the audio content to be played by the peripheral device in a first mode of operation of the peripheral device or to be played combined with noise cancelling content by the peripheral device in a second mode of operation of the peripheral device;
receive, from the peripheral device, information associated with a voice input received by the peripheral device from a person other than the first user during operation of the peripheral device in the second mode of operation;
determine, at least in part based on the information received from the peripheral device, whether the person is one of the interrupt-authorized contacts;
transmit an instruction to the peripheral device to switch from the second mode of operation to the first mode of operation if it is determined that the person is one of the interrupt-authorized contacts; and
transmit an instruction to the peripheral device to continue operation in the second mode of operation if it is determined that the person is not one of the interrupt-authorized contact.

### Claim 2 (depends on 1)

The device of claim 1, wherein the interrupt-authorized contacts are not authorized users of the device or the peripheral device, and wherein determining that the person is one of the interrupt-authorized contacts does not provide access, by the person, to any content at or from the device or the peripheral device.

### Claim 3 (depends on 1)

The device of claim 1, wherein the information associated with the voice input comprises the voice input, or a voice profile extracted from the voice input by the peripheral device.

### Claim 4 (depends on 3)

The device of claim 3, wherein the information associated with the voice input comprises the voice profile and further comprises an indication from an acoustic model stored in secure memory at the peripheral device that the person is a potential interrupt-authorized contact.

### Claim 5 (depends on 4)

The device of claim 4, wherein the acoustic model at the peripheral device is a first acoustic model, and wherein the one or more processors are configured to determine whether the person is one of the interrupt-authorized contacts by:
determining, with a second acoustic model at the device, whether the voice profile extracted from the voice input corresponds to one or more voice profiles associated with the interrupt-authorized contacts.

### Claim 6 (depends on 5)

The device of claim 5, wherein the one or more voice profiles have been received at the device from a second device of the person or from a remote server.

### Claim 7 (depends on 5)

The device of claim 5, wherein the first acoustic model and the second acoustic model have each been trained at the device.

### Claim 8 (depends on 7)

The device of claim 7, wherein the second acoustic model has been trained, at the device, using the one or more voice profiles.

### Claim 9 (depends on 8)

The device of claim 8, wherein the first acoustic model has been trained, at the device, using a training voice input that includes at least portion of a name of the first user.

### Claim 10 (depends on 5)

The device of claim 5, wherein the one or more processors are configured to determine whether the voice profile extracted from the voice input corresponds to one or more voice profiles associated the interrupt-authorized contacts, in part, based on recency information for the plurality of contacts stored at the device, frequency information for the plurality of contacts stored at the device, or a communication between the device and a second device of the person.

### Claim 11

A peripheral device of a first user, the peripheral device comprising:
a speaker;
a microphone; and
processing circuitry configured to:
operate the speaker to play audio content received from a first device of the first user in a first mode of operation;
operate the speaker to play the audio content combined with noise cancelling content generated using the microphone in a second mode of operation; and
while operating the speaker in the second mode of operation:
receive a voice input, with the microphone, from a person other than the first user;
determine, at least in part using an acoustic model stored in secure memory at the peripheral device, whether the person has been designated, at the first device, as an interrupt-authorized contact;
switch the operation of the speaker to the first mode of operation if it is determined that the person is the interrupt-authorized contact; and
continue operation of the speaker in the second mode of operation if it is determined that the person is not the interrupt-authorized contact.

### Claim 12 (depends on 11)

The peripheral device of claim 11, wherein the acoustic model at the peripheral device has been trained at the first device.

### Claim 13 (depends on 12)

The peripheral device of claim 12, wherein the acoustic model at the peripheral device is a first acoustic model, and wherein the processing circuitry of the peripheral device is configured to determine, at least in part using the acoustic model at the peripheral device, whether the person has been designated, at the first device, as the interrupt-authorized contact by:
determining, using the first acoustic model, that the person is a potential interrupt-authorized contact;
providing information associated with the voice input to the first device responsive to determining that the person is the potential interrupt-authorized contact; and
receiving, from the first device responsive to providing the information, an instruction to switch the operation of the speaker to the first mode of operation.

### Claim 14 (depends on 13)

The peripheral device of claim 13, wherein the instruction from the first device is based on:
a comparison, at the first device, of the information associated with the voice input to at least one voice profile associated with at least one contact that is identified, in secure memory at the first device, as being interrupt authorized; and
a determination, at the first device, of whether the person is the interrupt-authorized contact based on the comparison.

### Claim 15 (depends on 14)

The peripheral device of claim 14, wherein the at least one voice profile has been received at the first device from a second device of the person or from a remote server.

### Claim 16 (depends on 14)

The peripheral device of claim 14, wherein the comparison, at the first device, of the information associated with the voice input to at least one voice profile is based on:
an output of a second acoustic model at the first device responsive to the information associated with the voice input, the second acoustic model having been trained, at the first device, using the at least one voice profile.

### Claim 17 (depends on 13)

The peripheral device of claim 13, wherein the processing circuitry is configured to determine, using the first acoustic model, that the person is the potential interrupt-authorized contact by determining, using the first acoustic model, that the voice input includes at least portion of a name of the first user.

### Claim 18 (depends on 13)

The peripheral device of claim 13, wherein the processing circuitry is configured to determine, using the first acoustic model, that the person is a potential interrupt-authorized contact by determining, using the first acoustic model, that the voice input corresponds to a group of interrupt-authorized contacts.

### Claim 19 (depends on 12)

The peripheral device of claim 12, wherein the processing circuitry of the peripheral device is configured to determine, at least in part using the acoustic model at the peripheral device, whether the person has been designated, at the first device, as the interrupt-authorized contact using the acoustic model and using location information associated with the received voice input, the location information including at least one of proximity information and directional information and having been determined using the microphone and an additional microphone of an additional peripheral device of the first user, the additional peripheral device further including an additional speaker.

### Claim 20

A semiconductor device comprising processing circuitry configured to:
operate a speaker of a media output device of a first user to play audio content received from a first device of the first user in a first mode of operation;
operate the speaker to play the audio content combined with noise cancelling content generated using a microphone of the media output device in a second mode of operation; and
while operating the speaker in the second mode of operation:
receive a voice input, with the microphone, from a person other than the first user;
determine, at least in part using an acoustic model stored in secure memory at the media output device, whether the person has been designated, at the first device, as an interrupt-authorized contact;
switch the operation of the speaker to the first mode of operation if it is determined that the person is the interrupt-authorized contact; and
continue operation of the speaker in the second mode of operation if it is determined that the person is not the interrupt-authorized contact.
