Audio CAPTCHA with Distinguishable Primary Voice
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated systems can register multiple fictitious accounts at a faster rate than humans, leading to undesirable consequences such as spam, and existing techniques like CAPTCHA are not entirely effective in distinguishing humans from automated systems.
Innovation Solution
An audio challenge is generated with a distinguishable primary voice conveying key information and secondary voices conveying secondary information, which is mixed to create an audio content that humans can recognize but automated systems struggle with, allowing for human verification by identifying the key information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If CAPTCHA puzzles are used to distinguish humans from automated systems, then human verification is enabled, but automated systems may still solve them and human verification reliability is reduced
Solution Approach 1:
The patent changes the parameter domain from visual to auditory by using audio CAPTCHA challenges with multiple overlapping voices. This parameter change exploits the fact that automated visual recognition systems cannot easily process audio patterns, while human auditory processing remains robust. The primary voice is embedded within secondary voices at different pitch and timing parameters, creating a challenge that is reliable for human verification but difficult for automated systems to solve.
2Extent of automation
If visually cluttered images are used for CAPTCHA, then automated systems struggle to solve them, but accessibility issues arise for visually impaired users
Solution Approach 1:
The patent substitutes the visual mechanical system with an auditory system. Instead of presenting visually cluttered images that are inaccessible to visually impaired users, the invention uses audio challenges with multiple voices. This substitution maintains the anti-automation property while improving accessibility, as audio content can be processed by both visually impaired users and automated systems face difficulties with the complex audio pattern recognition required.
3Productivity
If automated systems register fictitious accounts at high speed, then productivity increases, but harmful factors such as spam increase
Solution Approach 1:
The patent applies preliminary anti-action by implementing audio CAPTCHA verification before allowing account registration. The audio challenge with embedded primary voice and overlapping secondary voices creates a barrier that automated systems cannot easily overcome. This preliminary verification step prevents automated high-speed registration of fictitious accounts before they can be used for spam, while still allowing legitimate human users to register accounts efficiently.
Data Source
AI summary
A system generates an audio challenge that includes a first voice and one or more second voices, the first voice being audibly distinguishable, by a human, from the one or more second voices. The first voice conveys first information and the second voice conveys second information. The system provides the audio challenge to a user and verifies that the user is human based on whether the user can identify the first information in the audio challenge.