# US 2023/0057442 A1 · Zero latency digital assistant

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

- Number: US 2023/0057442 A1
- Document ID: US20230057442A1
- Status: Published application
- Kind: A1
- Application number: 17/982,337
- Filed: 2022-11-07
- Published: 2023-02-23
- Earliest claimed: 2015-09-08
- Assignees: Apple Inc.
- Applicants: Apple Inc.
- Inventors: William F. STASIOR; David A. CARSON; Rohit DASARI; Yoon KIM
- Web page: https://patentgrep.com/patent/US20230057442A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 3/038: Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry
- G06F 3/0481: based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F 3/0604: {Improving or facilitating administration, e.g. storage management}
- G06F 3/0656: {Data buffering arrangements}
- G06F 3/0673: {Single storage device}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G10L 15/285: {Memory allocation or algorithm optimisation to reduce hardware requirements}
- G10L 2015/088: {Word spotting}
- G10L 2015/223: {Execution procedure of a spoken command}
- H04M 2201/40: using speech recognition
- H04M 2250/74: with voice recognition means
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

An electronic device can implement a zero-latency digital assistant by capturing audio input from a microphone and using a first processor to write audio data representing the captured audio input to a memory buffer. In response to detecting a user input while capturing the audio input, the device can determine whether the user input meets a predetermined criteria. If the user input meets the criteria, the device can use a second processor to identify and execute a task based on at least a portion of the contents of the memory buffer.

## Claims

### Claim 1

A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device with a microphone, cause the device to:
while a main processor is in a low-power mode:
capture audio input from the microphone;
write, using a low-power processor, the captured audio input to a memory buffer; and
determine, using the low-power processor, whether a first portion of the buffered audio input includes a trigger phrase;
in accordance with a determination that the first portion of the buffered audio input includes the trigger phrase:
cause the main processor to exit the low-power mode; and
after causing the main processor to exit the low-power mode:
identify, using the main processor, a computing task based on a second portion of the buffered audio input; and
execute, using the main processor, the identified computing task; and
in accordance with a determination that the first portion of the buffered audio input does not include the trigger phrase, forgo causing the main processor to exit the low-power mode, identifying the computing task, and executing the computing task.

### Claim 2 (depends on 1)

The non-transitory computer-readable storage medium according to claim 1, wherein the main processor executes the identified computing task immediately, without requiring a further input from a user.

### Claim 3 (depends on 1)

The non-transitory computer-readable storage medium according to claim 1, wherein the trigger phrase corresponds to a request to launch a digital assistant session.

### Claim 4 (depends on 1)

The non-transitory computer-readable storage medium according to claim 1, wherein identifying the computing task includes launching a digital assistant on the main processor, and wherein identifying and executing the identified computing task is performed by the digital assistant.

### Claim 5 (depends on 4)

The non-transitory computer-readable storage medium according to claim 4, further comprising instructions to cause the electronic device to:
further in accordance with the determination that the first portion of the buffered audio input includes the trigger phrase, provide the second portion of the buffered audio input to the digital assistant.

### Claim 6 (depends on 5)

The non-transitory computer-readable storage medium according to claim 5, wherein providing the second portion of the buffered audio input to the digital assistant includes providing the second portion of the buffered audio input to a remote server associated with the digital assistant.

### Claim 7 (depends on 4)

The non-transitory computer-readable storage medium according claim 4, wherein launching the digital assistant includes displaying a user interface associated with the digital assistant.

### Claim 8 (depends on 7)

The non-transitory computer-readable storage medium according to claim 7, wherein the user interface associated with the digital assistant is displayed in a full-screen view.

### Claim 9 (depends on 4)

The non-transitory computer-readable storage medium according to claim 4, wherein launching the digital assistant includes activating one or more audio components on the device.

### Claim 10 (depends on 4)

The non-transitory computer-readable storage medium according to claim 4, further comprising instructions to cause the electronic device to:
further in accordance with the determination that the first portion of the buffered audio input includes the trigger phrase:
activating a second microphone on the device, and
streaming audio detected by the second microphone to the digital assistant.

### Claim 11 (depends on 1)

The non-transitory computer-readable storage medium according to claim 1, further comprising instructions to cause the electronic device to:
in accordance with a determination that the first portion of the buffered audio does not correspond to an authorized user, forgoing to cause the main processor to exit the low-power mode, to identify the computing task, and to execute the computing task.

### Claim 12

A method, comprising:
at an electronic device including a microphone, and one or more processors:
while a main processor is in a low-power mode:
capturing audio input from the microphone;
writing, using a low-power processor, the captured audio input to a memory buffer; and
determining, using the low-power processor, whether a first portion of the buffered audio input includes a trigger phrase;
in accordance with a determination that the first portion of the buffered audio input includes the trigger phrase:
causing the main processor to exit the low-power mode; and
after causing the main processor to exit the low-power mode:
identifying, using the main processor, a computing task based on a second portion of the buffered audio input; and
executing, using the main processor, the identified computing task; and
in accordance with a determination that the first portion of the buffered audio input does not include the trigger phrase, forgoing causing the second processor to exit the low-power mode, identifying the computing task, and executing the computing task.

### Claim 13

An electronic device, comprising:
a microphone;
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
while a main processor is in a low-power mode:
capturing audio input from the microphone;
writing, using a low-power processor, the captured audio input to a memory buffer; and
determining, using the low-power processor, whether a first portion of the buffered audio input includes a trigger phrase;
in accordance with a determination that the first portion of the buffered audio input includes the trigger phrase:
causing the main processor to exit the low-power mode; and
after causing the main processor to exit the low-power mode:
identifying, using the main processor, a computing task based on a second portion of the buffered audio input; and
executing, using the main processor, the identified computing task; and
in accordance with a determination that the first portion of the buffered audio input does not include the trigger phrase, forgoing causing the second processor to exit the low-power mode, identifying the computing task, and executing the computing task.
