Motion-Sensed Keyword Detection for Low-Power Voice Activation

Solution Overview

Problem

Existing voice control systems in intelligent automated assistants require additional user inputs to activate voice detection, consume excessive power and processing resources when inactive, and are prone to false positives from ambient noise.

Innovation Solution

Utilizing motion sensors like accelerometers and gyroscopes to detect user mouth, face, and neck movements to recognize voice inputs, eliminating the need for audio detection and reducing power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If audio sensors continuously detect and process audio data to respond to voice inputs without additional activation inputs, then voice control responsiveness is improved, but power consumption and processing capacity increase

Engineering Contradiction:

Improvevoice control responsivenessVSAvoidpower consumption

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent replaces the audio-based voice detection system with a motion sensing system. Instead of using audio sensors to continuously monitor for voice commands, the system uses motion sensors (accelerometers, gyroscopes) to detect physical movements associated with speaking. This substitution eliminates the need for continuous audio processing while maintaining voice control functionality, thereby reducing power consumption and processing requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The motion sensing system operates periodically rather than continuously. The motion sensors are activated to detect specific movement patterns when needed, rather than continuously monitoring for audio inputs. This periodic operation significantly reduces the processing capacity and power consumption required compared to continuous audio monitoring.

Inventive Principle:

Principle #19Periodic action

2Ease of operation

If audio sensors continuously detect and process audio data to respond to voice inputs without additional activation inputs, then voice control responsiveness is improved, but processing capacity increases

Engineering Contradiction:

Improvevoice control responsivenessVSAvoidprocessing capacity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent replaces the audio-based voice detection system with a motion sensing system. Instead of using audio sensors to continuously monitor for voice commands, the system uses motion sensors (accelerometers, gyroscopes) to detect physical movements associated with speaking. This substitution eliminates the need for continuous audio processing while maintaining voice control functionality, thereby reducing power consumption and processing requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If audio sensors continuously detect audio data to respond to voice inputs, then voice control functionality is improved, but false positive responses increase due to ambient noise

Engineering Contradiction:

Improvevoice control functionalityVSAvoidfalse positive responses

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent replaces the audio-based voice detection system with a motion sensing system. Instead of using audio sensors to continuously monitor for voice commands, the system uses motion sensors (accelerometers, gyroscopes) to detect physical movements associated with speaking. This substitution eliminates the need for continuous audio processing while maintaining voice control functionality, thereby reducing power consumption and processing requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The motion data serves as an intermediary indicator of voice intent. Instead of directly detecting audio and risking false positives from ambient noise, the system uses motion patterns (mouth movement, head movement, etc.) as an intermediary signal to infer when a user intends to speak. This intermediary approach filters out false positives caused by ambient sounds while maintaining the ability to detect actual voice commands.

Inventive Principle:

Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Provides intuitive and efficient voice control with reduced power usage and minimized false positives by matching motion data to reference words or phrases, enabling seamless task initiation.

Implementation Method 1

Motion sensors such as accelerometers and gyroscopes can detect these motions

Methodology Applied

Scientific EffectAccelerometer: Accelerometer

Implementation Method 2

Motion sensors such as accelerometers and gyroscopes can detect these motions

Methodology Applied

Scientific EffectGyroscope: Gyroscope

Implementation Method 3

When a user speaks, the user's mouth, face, head, and neck move and vibrate

Methodology Applied

Scientific EffectVibration: Vibration

Data Source

PatentUS12525241B2Keyword detection using motion sensing

Publication Date: 2026.01.13 APPLE INC

AI summary

Systems and processes for operating an intelligent automated assistant are provided. In one embodiment, data is received from a motion sensor, for instance, recording the motion of a user as the user utters a spoken input. A determination is made whether a portion of the motion data matches reference data for a set of one or more words (e.g., a word or phrase). If so, a task associated with the one or more words is initiated in response.