Shared Voice Authentication for Personal and Guest Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech-enabled devices struggle to adequately distinguish between multiple users, particularly in securing access to personal information while allowing general use by guest users.
Innovation Solution
A speech-enabled device identifies the speaker through authentication tokens and visual information, classifying utterances as spoken by known users, and provides queries to a server with appropriate user indications, ensuring secure access to personal information while permitting general use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the device attempts to identify every speaker as a particular user, then personalized access to personal information is improved, but device complexity and processing requirements increase
Solution Approach 1:
The authentication system is segmented into multiple independent components: visual information processing module, authentication token verification module, and query routing module. Each module handles a specific aspect of user identification independently, reducing overall system complexity while maintaining high identification accuracy.
Solution Approach 2:
Authentication tokens serve as intermediaries between the speaker identification system and the personal information access system. The tokens encapsulate user credentials and permissions, allowing the system to verify user identity without exposing complex authentication logic in the main processing flow.
2Reliability
If the device restricts access to personal information only for identified users, then data security is improved, but ease of operation deteriorates due to limited guest access
Solution Approach 1:
Different access rights and authentication requirements are applied to different users based on their local characteristics. Registered users receive full access with visual-based authentication, while guest users receive limited access with simplified authentication, optimizing both security and convenience for each user type.
Solution Approach 2:
The system performs partial authentication for guest users (without requiring visual identification) while performing complete authentication for registered users. This partial action approach allows guest access to non-personal information while maintaining security for personal data.
3Adaptability or versatility
If the device stores multiple authentication tokens for different users, then adaptability to multiple users is improved, but memory requirements and processing overhead increase
Solution Approach 1:
Instead of storing complete user profiles and credentials, the system stores compact authentication tokens that contain essential verification information. These tokens are lightweight copies that enable user identification without requiring storage of extensive user data.
Solution Approach 2:
The authentication token format is designed to be universal across multiple users and devices. A single token structure can represent any registered user, eliminating the need for user-specific storage schemas and reducing overall data requirements through standardized multi-functional design.
4Measurement precision
If the device uses visual information for speaker identification, then measurement precision of user identity is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
Visual information processing is performed as a preliminary action before query processing. The system captures and processes visual data to identify the speaker and retrieve authentication tokens in advance, separating the complex visual processing task from the main query handling flow.
Solution Approach 2:
The system replaces complex mechanical speaker identification methods with visual information processing using cameras and image recognition algorithms. This substitution enables more accurate identification while allowing the complex processing to be handled by specialized vision processing hardware and software.
Data Source
AI summary
In some implementations, processor(s) can receive an utterance from a speaker, and determine whether the speaker is a known user of a user device or not a known user of the user device. The user device can be shared by a plurality of known users. Further, the processor(s) can determine whether the utterance corresponds to a personal request or non-personal request. Moreover, and in response to determining that the speaker not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request, the processor(s) can cause a response to the utterance to be provided for presentation to the speaker at the user device response to the utterance, or can cause an action to be performed by the user device responsive to the utterance.