Analog Natural Speech Detection for Replay-Resistant Microphones

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing voice biometrics systems struggle to differentiate between natural speech and replayed speech, leading to high power consumption in battery-powered devices due to the inability of conventional voice activity detectors to distinguish between the two, especially in the presence of television or radio playback.

Innovation Solution

Implementing a low-power natural speech detection module in the analogue domain within a microphone to differentiate between natural and replayed speech by analyzing frequency bands and power ratios, reducing the need for power-intensive digital processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional voice activity detectors are used to detect speech, then speech processing can be activated, but power consumption increases significantly when replayed speech is detected

Engineering Contradiction:

Improvespeech processing activationVSAvoidpower consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The detection system is segmented into multiple stages: a first detector analyzes low-frequency bands (below 200 Hz) for power loss characteristics, and a second detector analyzes high-frequency bands (above 8 kHz) for modulation patterns. This segmentation allows the system to identify replayed speech through specific frequency band analysis, preventing unnecessary activation of power-intensive speech processing when only replayed speech is detected.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If digital signal processing is used to detect replayed speech, then detection accuracy improves, but power consumption increases

Engineering Contradiction:

Improvereplayed speech detection accuracyVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent replaces complex digital signal processing with analogue domain analysis. The first detector uses analogue power loss detection in low-frequency bands, and the second detector uses analogue modulation rate analysis in high-frequency bands. This substitution maintains detection accuracy while significantly reducing power consumption compared to full digital processing approaches.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Use of energy by moving object

If the natural speech detection module operates in the analogue domain, then power consumption is reduced, but processing capability is limited

Engineering Contradiction:

Improvepower consumptionVSAvoidprocessing capability

Core Design Contradiction:

Use of energy by moving objectVSDevice complexity

Solution Approach 1:

The analogue domain detectors serve as intermediaries that perform initial screening of the audio signal. The first detector checks for power loss in low frequencies, and the second detector checks for appropriate modulation rates in high frequencies. Only when both analogue checks pass does the system proceed to digital speech processing, thus reducing overall power consumption while maintaining necessary processing capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20260094613A1Natural speech detection

Publication Date: 2026.04.02 CIRRUS LOGIC INT SEMICON LTD

AI summary

A microphone device, comprising: a microphone configured to generate an audio signal; a natural speech detection module for detecting natural speech in the first audio signal; wherein, on detection of the natural speech in the first audio signal, the natural speech detection module is configured to output a trigger signal to a speech processing module to process the natural speech in the audio signal.