Audio Trigger Word Misrecognition Detection and Confirmation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Audio recognition systems often experience misrecognition of trigger words, leading to unnecessary activation of functions, which can result in incorrect execution of user intents.
Innovation Solution
A method and device that determine if a preset trigger word is misrecognized by analyzing the audio signal's similarity to a reference signal, adjusting the intensity of the reference signal, and requesting additional user input to confirm the intended action before executing the corresponding function.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If audio recognition is activated by recognizing trigger words, then the system can automatically execute functions, but misrecognition of trigger words occurs leading to incorrect function activation
Solution Approach 1:
The system requests additional user input when misrecognition is detected, creating a feedback loop that allows the user to confirm or correct the recognized trigger word before function execution, thereby resolving the contradiction between automation and reliability
Solution Approach 2:
The system performs preliminary verification by analyzing audio signal characteristics and comparing them against reference signals before executing the function, preventing incorrect activation while maintaining automated operation
2Reliability
If the system requests additional user input to confirm trigger words, then misrecognition is reduced, but the response time and user interaction complexity increase
Solution Approach 1:
The system applies additional verification steps (partial action) only when misrecognition is detected rather than for all trigger word recognitions, reducing the time penalty while maintaining high reliability for problematic cases
Solution Approach 2:
The additional input mechanism serves multiple functions: confirming trigger words, correcting misrecognition, and providing user feedback, thereby justifying the time investment through multifunctional benefit
Data Source
AI summary
A method, an electronic device, and a non-transitory computer-readable medium storing instructions may be provided. The method may include receiving an audio signal; based on at least one preset trigger word being included in the received audio signal, determining whether the at least one trigger word included in the audio signal is misrecognized; based on the determining that the at least one preset trigger word is misrecognized, requesting an additional input from a user; and based on the additional input received in response to the request and the audio signal, executing a function corresponding to audio recognition.


