Voice Authentication Using Variable Utterance Length Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voiceprint authentication systems require users to utter for a time equal to or longer than a predetermined value for registration and authentication, which is inconvenient for users.
Innovation Solution
An authentication system that detects utterance sections, collates voice signals based on utterance length or syllable count, and sets authentication conditions accordingly to improve user convenience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a predetermined minimum utterance time is required for voiceprint registration and authentication, then authentication accuracy is maintained, but user convenience deteriorates due to fixed time requirements
Solution Approach 1:
The patent applies dynamics by making the authentication condition variable rather than fixed. The determination unit dynamically adjusts the required utterance time based on the individual user's registered voice characteristics, including their natural speaking pace and voiceprint quality. This allows the system to adapt to each user's unique speech patterns while maintaining authentication accuracy.
Solution Approach 2:
The patent changes the parameter of authentication time requirement from a fixed predetermined value to a variable determined by the user's registered utterance characteristics. The determination unit calculates appropriate authentication conditions based on the total time length of registered utterances and other voice features, thereby optimizing both accuracy and convenience for each user.
2Stability of the object's composition
If a fixed predetermined utterance time is required for all users, then authentication consistency is maintained, but individual user characteristics are not optimized
Solution Approach 1:
The patent applies local quality by customizing authentication conditions for each individual user based on their specific voice characteristics. The determination unit analyzes the registered voice data of each user and sets authentication parameters tailored to their natural speaking pace, voice quality, and utterance patterns. This allows each user to have optimized authentication conditions while the system maintains overall consistency through standardized determination processes.
Solution Approach 2:
The patent uses preliminary action by analyzing and storing the user's voice characteristics during the registration phase. The system pre-calculates appropriate authentication conditions based on the registered utterance data, including total time length and voice features. This preliminary analysis enables the system to automatically determine suitable authentication parameters before actual authentication occurs, optimizing both consistency and user-specific adaptation.
Data Source
AI summary
An authentication system includes an acquisition unit configured to acquire a voice signal of an utterance voice of a speaker; a detection unit configured to detect a first utterance section during which the speaker is uttering from the voice signal and a second utterance section during which the speaker is uttering from voice signals of a plurality of speakers registered in a database; a determination unit configured to collate a first voice signal of the first utterance section with a second voice signal of the second utterance section and determine an authentication condition for authentication using the first voice signal based on a length of the second voice signal of the second utterance section or the number of syllables included in the second utterance section; and an authentication unit configured to authenticate the speaker based on the authentication condition.