Spoken Free-Form Passwords for Lightweight Speaker Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional password security systems based on textual passwords are vulnerable to unauthorized access and malicious attacks, and biometric speech verification technologies are costly and not always justified by their benefits.
Innovation Solution
A speech processing system using spoken free-form passwords with standard speech recognition engines, where users create and authenticate with unique, voice-specific acoustic baseforms that are resistant to hacking, leveraging commercial off-the-shelf speech processing systems to provide lightweight speaker verification without the need for costly infrastructure upgrades.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If specialized speaker identification and verification (SIV) technologies are used, then user authentication security is improved, but system cost increases significantly
Solution Approach 1:
The patent combines text-based password recognition with speaker verification capabilities into a unified speech recognition system. The system processes both the linguistic content and acoustic characteristics of speech through integrated modules, allowing simultaneous password verification and speaker identification without requiring separate specialized SIV hardware or software systems.
Solution Approach 2:
The speech recognition system is designed to perform multiple functions: it can recognize spoken passwords, verify speaker identity, and provide authentication services. This multi-functional approach eliminates the need for dedicated SIV systems while maintaining security requirements, as the same speech processing infrastructure serves both password recognition and speaker verification purposes.
2Device complexity
If text-based passwords are used, then system simplicity is maintained, but security against malicious attacks deteriorates
Solution Approach 1:
The authentication mechanism uses a composite approach by combining two distinct security factors: the linguistic content of the password (what is said) and the acoustic characteristics of the speaker (how it is said). This dual-factor verification method creates a more robust security system that remains conceptually simple while significantly improving resistance to attacks compared to text-based passwords alone.
3Reliability
If spoken passwords with acoustic baseforms are used, then security against hacking is improved, but processing complexity increases
Solution Approach 1:
The system performs preliminary processing by converting spoken passwords into acoustic baseforms during the authentication phase. These acoustic baseforms serve as standardized representations that can be efficiently stored and compared against stored password templates. This preliminary conversion simplifies subsequent verification operations while maintaining high security through the use of voice-specific acoustic characteristics.
Data Source
AI summary
The present invention discloses a system and a method for authenticating a user based upon a spoken password processed though a standard speech recognition engine lacking specialized speaker identification and verification (SIV) capabilities. It should be noted that the standard speech recognition grammar can be capable of acoustically generating speech recognition grammars in accordance with the cross referenced application indicated herein. The invention can prompt a user for a free-form password and can receive a user utterance in response. The utterance can be processed through a speech recognition engine (e.g., during a grammar enrollment operation) to generate an acoustic baseform. Future user utterances can be matched against the acoustic baseform. Results from the future matches can be used to determine whether to grant the user access to a secure resource.