Voice Recognition Correction Strategy for Motor Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In speech recognition systems, when a user repeats or corrects their input, it is often unclear whether the second input is a repetition or a new input, leading to unnecessary presentation of incorrect recognition results.
Innovation Solution
A method that recognizes content repetition in speech inputs by analyzing literal repetition, alternative formulations, prosodic differences, or user actions, and uses this recognition to exclude incorrect results from the output list, thereby preventing false recognition results from being presented again.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the speech recognition system processes the second speech input in the same manner as the first input, then the system maintains simple processing logic, but false recognition results are unnecessarily presented again to the user
Solution Approach 1:
The system performs preliminary identification of repetition patterns before final recognition result generation. By detecting whether the second speech input repeats the first input's content (through literal repetition detection or alternative formulation analysis), the system pre-determines which recognition results should be excluded from the output list, preventing false results from being presented again without requiring complex post-processing
Solution Approach 2:
The system uses feedback from the user's second speech input to modify the recognition process. When a repetition pattern is detected, the system feedback-adjusts the recognition results by excluding previously presented false results, thereby improving reliability while maintaining relatively simple processing logic through the feedback loop
2Loss of information
If the system presents all recognition results from the second speech input, then the user has complete information, but unnecessary repetition of incorrect results increases time loss
Solution Approach 1:
The system extracts and removes the harmful element (false recognition results) from the output list. By identifying which recognition results from the first speech input should be excluded based on repetition detection, the system selectively presents only the relevant new recognition results from the second input, saving time while maintaining information completeness for valid results
3Adaptability or versatility
If the system uses alternative formulations for speech input, then the system becomes more adaptable to user speech patterns, but it becomes more difficult to distinguish between corrections and new inputs
Solution Approach 1:
The system segments the speech input analysis into distinct components: identifying the core speech content, detecting repetition patterns, and determining user intent. By breaking down the complex task of distinguishing corrections from new inputs into separate analytical steps (content comparison, repetition detection, formulation analysis), the system handles alternative formulations while maintaining clear differentiation between correction and new input scenarios
Data Source
AI summary
The invention relates to a method for operating a motor vehicle, wherein a first speech input of a user is received, at least one recognition result (A-D) is determined by means of a speech recognition system, at least one recognition result (A-D) is output to an output device of the motor vehicle as a result list and a second speech output of the user is received. The objective of the invention is to avoid a double input of false recognition results. In the second speech input, first, a content input repetition of the first speech input is recognized, which points to a correction request of the user. As a result, an excludable portion of the result list is determined and with the determination of a recognition result (C-E) for the second speech input, the excludable portion is excluded as a possible recognition result.