Low Power Voice Wake-Up System Using Segmented Processing

Solution Overview

Problem

Current voice wake-up systems in electronic devices require additional digital processing circuits, leading to increased device cost and power consumption, which fails to comply with energy requirements.

Innovation Solution

A processing system operating in a first power domain with a memory and processing circuit to detect sound data, transferring it to a second memory for voice data analysis, using a low power core processing circuit to determine if the voice data matches a predetermined command, thereby reducing overall power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If an additional digital processing circuit is used to analyze voice commands, then voice wake-up function is achieved, but device cost and power consumption increase

Engineering Contradiction:

Improvevoice wake-up functionVSAvoidpower consumption

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by stationary object

Solution Approach 1:

The patent divides the voice processing system into two distinct parts: a low-power domain handling basic voice detection and a high-power domain handling complex voice command analysis. This segmentation allows the system to achieve voice wake-up functionality while minimizing overall power consumption by keeping only the essential low-power components active during standby.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary mechanism (the voice detection circuit in the low-power domain) that acts as a gateway between the inactive high-power processing circuit and the incoming voice signals. This intermediary detects wake-up keywords and triggers the high-power circuit only when necessary, thereby reducing unnecessary power consumption while maintaining full voice command analysis capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If an additional digital processing circuit is used to analyze voice commands, then voice wake-up function is achieved, but device cost increases

Engineering Contradiction:

Improvevoice wake-up functionVSAvoiddevice cost

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the voice processing system into two distinct parts: a low-power domain handling basic voice detection and a high-power domain handling complex voice command analysis. This segmentation allows the system to achieve voice wake-up functionality while minimizing overall power consumption by keeping only the essential low-power components active during standby.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary mechanism (the voice detection circuit in the low-power domain) that acts as a gateway between the inactive high-power processing circuit and the incoming voice signals. This intermediary detects wake-up keywords and triggers the high-power circuit only when necessary, thereby reducing unnecessary power consumption while maintaining full voice command analysis capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If additional digital processing circuits are added for voice analysis, then voice recognition capability is improved, but power consumption increases

Engineering Contradiction:

Improvevoice recognition capabilityVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent divides the voice processing system into two distinct parts: a low-power domain handling basic voice detection and a high-power domain handling complex voice command analysis. This segmentation allows the system to achieve voice wake-up functionality while minimizing overall power consumption by keeping only the essential low-power components active during standby.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system employs periodic action by keeping the high-power processing circuit in a low-power sleep state and only activating it periodically when the low-power voice detection circuit detects a wake-up keyword. This approach maintains high voice recognition capability when needed while dramatically reducing average power consumption during idle periods.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentEP3678133B1Processing system and voice detection method

Publication Date: 2024.06.05 REALTEK SEMICON CORP

Figure 1
Figure 2
Figure 3

AI summary

A processing system operates in a first power domain and includes a first memory, a memory access circuit, and a first processing circuit. The first memory stores sound data detected by a microphone. The memory access circuit transfers the sound data to a second memory according to a first command, in order to store the sound data as voice data. The first processing circuit outputs a second command according to a human voice detection signal. The second command is for enabling a second processing circuit, in order to determine whether the voice data in the second memory matches a predetermined voice command. One of the first and the second processing circuits outputs the first command. The second processing circuit operates in a second power domain. A power consumption to which the first power domain corresponds is lower than a power consumption to which the second power domain corresponds.