Voice Wake-Up Detection Using Syllable and Frequency Characteristics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current voice wake-up mechanisms in electronic devices result in high power consumption due to frequent processor wake-ups for false voice command determinations, preventing the device from entering a true standby state.

Innovation Solution

A voice wake-up apparatus and method utilizing a voice activity detection circuit, storage circuit, and smart detection circuit that performs time and frequency domain detections to generate syllable and frequency characteristic results, comparing these to a predetermined voice sample to accurately identify wake-up commands and reduce unnecessary processor wake-ups.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If the processor performs frequent voice command determinations, then the voice wake-up responsiveness is improved, but the power consumption increases

Engineering Contradiction:

Improvevoice wake-up responsivenessVSAvoidpower consumption

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

The voice processing system is segmented into two distinct stages: a first processing stage performed by a low-power voice wake-up processor that performs syllable and frequency analysis, and a second processing stage performed by a high-power main processor that performs full voice command recognition. This segmentation allows the system to maintain responsive voice detection while minimizing power consumption by keeping the main processor in sleep mode during standby.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A voice wake-up processor acts as an intermediary between the microphone and the main processor. It performs preliminary voice activity detection, syllable counting, and frequency spectrum analysis to filter out false alarms before activating the main processor, thereby reducing unnecessary wake-ups and power consumption.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If the processor remains active for voice determination, then the voice command detection accuracy is improved, but the device cannot enter standby state

Engineering Contradiction:

Improvevoice command detection accuracyVSAvoidstandby state duration

Core Design Contradiction:

ReliabilityVSDuration of action of stationary object

Solution Approach 1:

The voice wake-up processor performs preliminary voice activity detection, syllable counting, and frequency analysis before activating the main processor. This preliminary action ensures that only genuine voice commands trigger the high-power processor, maintaining detection accuracy while enabling the device to remain in standby state during non-command periods.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system performs partial voice processing (syllable counting and frequency spectrum analysis) rather than complete voice command recognition during standby mode. This partial action is sufficient to filter false alarms and maintain reliable wake-up detection while allowing the device to stay in low-power standby state.

Inventive Principle:

Principle #16Partial or excessive action

3Use of energy by moving object

If the processor performs occasional determination, then the power consumption is reduced, but the false acceptance rate increases

Engineering Contradiction:

Improvepower consumptionVSAvoidfalse acceptance rate

Core Design Contradiction:

Use of energy by moving objectVSReliability

Solution Approach 1:

The voice wake-up processor performs preliminary syllable counting and frequency spectrum analysis to establish voice characteristics before triggering the main processor. This preliminary action creates a more reliable filtering mechanism that reduces false acceptance rates even when the main processor operates occasionally in standby mode.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the parameters used for voice detection from simple voice activity detection to a multi-parameter approach including syllable counting and frequency spectrum analysis. These parameter changes enable more accurate discrimination between genuine commands and false alarms, reducing the false acceptance rate while maintaining low power consumption.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11250849B2Voice wake-up detection from syllable and frequency characteristic

Publication Date: 2022.02.15 REALTEK SEMICON CORP

AI summary

A voice wake-up apparatus used in an electronic device that includes a voice activity detection circuit, a storage circuit and a smart detection circuit is provided. The voice activity detection circuit receives an input sound signal and detects a voice activity section of the input sound signal. The storage circuit stores a predetermined voice sample. The smart detection circuit receives the input sound signal to perform a time domain and a frequency domain detection on the voice activity section to generate a syllable and frequency characteristic detection result, compare the syllable and frequency characteristic detection result with the predetermined voice sample and generate a wake-up signal to a processing circuit of the electronic device when the syllable and frequency characteristic detection result matches the predetermined voice sample to wake up the processing circuit.