Voice Activation Threshold Adjustment for Vehicle Noise

Solution Overview

Problem

Noise in voice signals processed by noise reduction hardware modules in vehicles affects the accuracy of voice activation systems, increasing costs due to the need for additional hardware and circuit adjustments in onboard devices.

Innovation Solution

A voice activation method and apparatus that calculates an acoustic score for activation keywords and dynamically adjusts a voice activation threshold based on the noise level, allowing for successful voice activation operations without the need for noise reduction hardware, thereby improving success rates and reducing costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If a noise reduction hardware module is added to the microphone, then noise reduction capability is improved, but device cost and circuit complexity increase

Engineering Contradiction:

Improvenoise in voice signalVSAvoidcircuit complexity

Core Design Contradiction:

Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical hardware noise reduction module with a software-based acoustic score calculation system. The processor calculates an acoustic score based on the voice signal characteristics and compares it with a threshold to determine activation, eliminating the need for additional noise reduction hardware while maintaining voice activation functionality in noisy environments.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameter used for voice activation from simple noise-reduced signal levels to a calculated acoustic score. This score is derived from multiple voice signal parameters including energy, pitch, and timbre characteristics, allowing the system to adaptively determine activation based on the overall acoustic quality rather than relying on hardware noise filtering.

Inventive Principle:

Principle #35Parameter changes

2Object-affected harmful factors

If a noise reduction hardware module is added to the microphone, then noise reduction capability is improved, but device cost increases

Engineering Contradiction:

Improvenoise in voice signalVSAvoiddevice cost

Core Design Contradiction:

Object-affected harmful factorsVSEase of manufacture

Solution Approach 1:

The patent replaces the mechanical hardware noise reduction module with a software-based acoustic score calculation system. The processor calculates an acoustic score based on the voice signal characteristics and compares it with a threshold to determine activation, eliminating the need for additional noise reduction hardware while maintaining voice activation functionality in noisy environments.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses computationally inexpensive algorithms to calculate the acoustic score from existing voice signal data, replacing expensive hardware modules. The solution leverages processing power already present in modern devices to perform what would otherwise require dedicated hardware, significantly reducing manufacturing costs.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Object-affected harmful factors

If a noise reduction hardware module is added to the microphone, then noise reduction capability is improved, but the activation accuracy in noisy environments deteriorates

Engineering Contradiction:

Improvenoise in voice signalVSAvoidactivation accuracy

Core Design Contradiction:

Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent changes the parameter used for voice activation from simple noise-reduced signal levels to a calculated acoustic score. This score is derived from multiple voice signal parameters including energy, pitch, and timbre characteristics, allowing the system to adaptively determine activation based on the overall acoustic quality rather than relying on hardware noise filtering.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent implements a feedback mechanism where the calculated acoustic score is continuously compared with a predetermined threshold. The system uses this comparison feedback to determine whether to activate the voice processing function, creating an adaptive decision-making process that improves activation accuracy in varying noise conditions.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11069343B2Voice activation method, apparatus, electronic device, and storage medium

Publication Date: 2021.07.20 TENCENT TECHNOLOGY (SHENZHEN) CO LTD

AI summary

Embodiments of the present disclosure disclose a voice activation method, an apparatus, an electronic device, and a storage medium thereof. The voice activation method includes: capturing a voice signal in a vehicle; calculating an acoustic score of an activation keyword extracted from the voice signal, the acoustic score being used for indicating authenticity of the activation keyword, the authenticity of the activation keyword being a probability that the activation keyword is used for waking up the electronic device to perform a voice activation operation, and a magnitude of the acoustic score being positively correlated to a magnitude of the probability; determining a voice activation threshold according to a noise level in the vehicle, a magnitude of the voice activation threshold being negatively correlated to a magnitude of the noise; and performing the voice activation operation when the acoustic score is greater than the voice activation threshold.