Voiceprint Registration via Automatic Speech Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voiceprint registration methods are complex and difficult for users to implement, requiring repetitive operations such as reading text on devices, which hinders user convenience and adoption.
Innovation Solution
A voiceprint registration method that acquires and processes speech information to extract features, determines if they are associated with a smart device, and sets them as user identification without requiring specific user operations, using modules for feature extraction, recognition, and association.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed registration procedure is used (reading text repeatedly on mobile terminal or far field device), then the voiceprint registration can be completed, but the operation process becomes complex and user convenience deteriorates
Solution Approach 1:
The system automatically captures speech information from the smart device's microphone, extracts voiceprint features, and completes registration without requiring users to read text or perform repeated operations. The device serves itself by utilizing its own speech recognition capabilities to register the user's voiceprint.
Solution Approach 2:
The system pre-configures the voiceprint registration to occur automatically during normal device usage. By capturing speech information in advance during natural device interaction, the system eliminates the need for a separate, complex registration procedure.
2Ease of operation
If explicit user operations are required for voiceprint registration, then the registration process can be controlled, but the productivity and adoption rate deteriorate
Solution Approach 1:
The system performs voiceprint extraction and registration automatically using the smart device's own speech recognition system. Users simply need to speak naturally during device interaction, and the system completes the entire registration process autonomously without requiring explicit user operations or controls.
Solution Approach 2:
The patent replaces manual user operations (reading text, pressing buttons, confirming steps) with an automated speech recognition system. The mechanical interaction of following registration instructions is substituted by an acoustic field-based automatic recognition and feature extraction system.
Data Source
AI summary
Embodiments of the present disclosure provide a voiceprint registration method, a server and a storage medium. The method may include: acquiring present speech information collected by a smart device; extracting a present voiceprint feature of the present speech information; determining whether the present voiceprint feature is a voiceprint feature associated with the smart device; and determining the present voiceprint feature as a user identification associated with the smart device to determine the present voiceprint feature as the voiceprint feature associated with the smart device, in response to determining that the present voiceprint feature is not the voiceprint feature associated with the smart device.