Voiceprint Clustering for Automatic User Registration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice-based user registration processes for intelligent devices are complex and cumbersome, requiring multiple wake-up voices and a username input, leading to a poor user experience.

Innovation Solution

A method that extracts and stores voiceprint features each time a wake-up voice is received, clusters them into categories, and assigns category identifiers for user registration, allowing identification without the need for multiple wake-up voices or username inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the existing voice-based user registration process is used (requiring multiple wake-up voices and username input), then user identification accuracy is improved, but operation complexity increases and user experience deteriorates

Engineering Contradiction:
Improveuser identification accuracyVSAvoidregistration operation simplicity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system performs automatic user registration by extracting voiceprint features from wake-up voices without requiring user intervention for username input. The device autonomously completes the registration process by storing the extracted voiceprint features, eliminating the need for users to manually enter information while maintaining identification accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent extracts only the essential voiceprint features from wake-up voices for user registration, separating this critical identification element from the cumbersome username input process. By focusing solely on voiceprint extraction and storage, the system achieves accurate user identification while dramatically simplifying the registration operation.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If multiple wake-up voices are required for registration, then voiceprint feature reliability is improved, but registration time increases

Engineering Contradiction:
Improvevoiceprint feature reliabilityVSAvoidregistration time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system continuously extracts and accumulates voiceprint features from multiple wake-up voices in sequence, maintaining the reliability benefits of multi-sample collection while streamlining the process. The continuous extraction and automatic storage of features eliminates interruptions for username input, reducing overall registration time while preserving voiceprint reliability.

Inventive Principle:
Principle #20Continuity of useful action

3Adaptability or versatility

If username input is required during registration, then user account management is improved, but device complexity increases

Engineering Contradiction:
Improveaccount management capabilityVSAvoidregistration process complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical interaction of username input (keyboard typing or selection) with automatic voiceprint-based identification. By substituting the manual account management process with automated voice feature extraction and storage, the system maintains account management capabilities while significantly reducing the complexity of the registration process.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3611895B1Method and device for user registration, and electronic device
Publication Date: 2024.04.10 BEIJING ORION STAR TECH CO LTD
  • EP3611895B1 patent drawingFigure 1
  • EP3611895B1 patent drawingFigure 2
  • EP3611895B1 patent drawingFigure 3~5

AI summary

Provided in embodiments of the present application are a method and apparatus for user registration and electronic device. The method includes: after obtaining a wake-up voice of a user each time, extracting and storing a first voiceprint feature corresponding to the wake-up voice; clustering the stored first voiceprint features to divide the stored first voiceprint features into at least one category, wherein, each of the at least one category includes at least one first voiceprint feature which belongs to the same user; assigning one category identifier to each category; storing each category identifier in correspondence to at least one first voiceprint feature corresponding to this category identifier to complete user registration. The embodiments of the present application can simplify the user operation and improve the user experience.