Voice Recognition Stability Verification for Registration Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voice registration systems are prone to registration errors due to non-steady noise and erroneous voice section detection, leading to recognition errors and inefficient memory usage.
Innovation Solution
A voice recognition system that requires multiple utterances for registration, using a stability verification unit to determine similarity and create a standard pattern only when the similarity exceeds a threshold, and includes a re-utterance request mechanism to ensure stable voice data registration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If only one utterance is received for registration, then the registration process is simple and quick, but registration errors occur due to non-steady noise and erroneous voice section detection
Solution Approach 1:
The system performs preliminary stability verification by comparing multiple utterances before final registration. The stability verification unit compares the input utterance with previously registered standard patterns to determine if the utterance is stable and free from noise interference, ensuring reliable registration before the utterance is committed to the standard pattern storage
Solution Approach 2:
The system implements feedback through the stability verification process. When an utterance is input, it is compared with existing standard patterns, and the registration result is determined based on whether the utterance demonstrates stability across multiple comparisons. This feedback mechanism prevents erroneous registration while maintaining efficient processing
2Reliability
If multiple utterances are required for registration, then registration stability is improved, but the number of utterances increases and memory usage increases
Solution Approach 1:
The system extracts only the essential stability information from multiple utterances. Instead of storing all raw utterance data, the stability verification unit extracts stability metrics by comparing utterances with standard patterns, and only retains the verified stable utterance for registration. This reduces the quantity of stored data while maintaining registration reliability
Solution Approach 2:
The system changes the evaluation parameter from raw utterance count to stability score. By evaluating utterances based on their stability characteristics rather than simply requiring a fixed number of utterances, the system can achieve reliable registration with fewer actual utterances, thereby reducing memory usage while maintaining accuracy
Data Source
AI summary
A voice recognition system includes: a voice input unit 11 for inputting a voice uttered a plurality of times; a registering voice data storage unit 12 for storing voice data uttered the plurality of times and input into the voice input unit 11; an utterance stability verification unit 13 for determining a similarity between the voice data uttered the plurality of times that are read from the registering voice data storage unit 12, and determining that registration of the voice data is acceptable when the similarity is greater than a threshold Tl; and a standard pattern creation unit 14 for creating a standard pattern by using the voice data where the utterance stability verification unit 13 determines that registration is acceptable.


