Speech Recognition Device Dynamic Disturbance Sound Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition devices do not effectively prevent uttered content from being heard by third parties, as they do not adequately control disturbance sounds, leading to potential eavesdropping in situations where privacy is desired.
Innovation Solution
A speech recognition device with a controller that adjusts output volume and type of sound based on whether the content is intended to be private, using a combination of speech recognition processing, audio reproduction, and volume setting units to suppress the content from being heard by others.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If music is output at a comfortable volume for the user, then the user can enjoy music, but third parties can hear the uttered content
Solution Approach 1:
The system dynamically adjusts the music volume based on the user's utterance state. When an utterance is detected, the music volume is automatically reduced to a level where third parties cannot hear the uttered content, and then restored after the utterance ends. This dynamic adjustment resolves the contradiction by making the volume adaptive rather than fixed.
Solution Approach 2:
The system changes the volume parameter of the music output based on the utterance detection state. By transitioning the volume parameter between different levels (normal level vs. reduced level), the system ensures privacy during utterances while maintaining normal music playback conditions otherwise.
2Object-affected harmful factors
If music volume is reduced to prevent third parties from hearing uttered content, then privacy is protected, but the user cannot enjoy music at comfortable volume
Solution Approach 1:
The system applies periodic action by temporarily reducing music volume only during the specific period when the user is uttering content, then restoring the normal volume after the utterance ends. This time-based periodic adjustment ensures privacy protection is applied only when necessary, maintaining user comfort during non-utterance periods.
Solution Approach 2:
The music volume is made dynamic rather than static, automatically adjusting between high and low levels based on utterance detection. This dynamic behavior allows the system to provide privacy protection when needed while maintaining comfortable music playback conditions when the user is not speaking.
3Object-affected harmful factors
If disturbance sound is output to mask uttered content from third parties, then privacy is protected, but speech recognition accuracy may deteriorate
Solution Approach 1:
The system extracts and removes the disturbance sound component from the input signal before performing speech recognition. By separating and eliminating the masking noise from the speech signal, the system can maintain high speech recognition accuracy while still providing privacy protection through controlled music volume adjustment.
Data Source
AI summary
A speech recognition device of the present disclosure recognizes an uttered speech of a user, and includes a controller configured to control output of any disturbance sound according to whether uttered content requested to the user is content desired not to be heard by a third party, and stop the output of the disturbance sound in response to end of an utterance of the user.