Voice Print Suitability Testing for IVR Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice biometric authentication methods are not suitable for self-service channels due to the limitations of short speech bursts, leading to inadequate performance and low pass rates, which deter users from adopting voice print technology for authentication.
Innovation Solution
Implementing a system that performs background suitability tests and filtering on voice prints to enroll only those with high authentication accuracy, using text-independent voice biometrics, and determining the maximum speech duration based on desired accuracy levels, allowing for passive authentication without active enrollment processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If text-independent voice biometrics are used in self-service channels with short speech bursts (3-5 seconds), then user experience is improved and active enrollment is avoided, but authentication accuracy becomes inadequate and pass rates are low
Solution Approach 1:
The system performs suitability testing in advance during enrollment to identify voice prints that will work reliably with short speech bursts. This preliminary action ensures that only suitable voice prints are enrolled for text-independent authentication in self-service channels, preventing authentication failures later.
Solution Approach 2:
The system changes the parameter of speech duration by determining maximum speech durations based on desired accuracy levels. This allows optimization of the authentication process by matching speech duration parameters to specific accuracy requirements, enabling reliable authentication even with constrained speech lengths.
2Productivity
If voice prints are enrolled without suitability testing, then enrollment process is simplified and faster, but authentication performance becomes inadequate
Solution Approach 1:
Suitability testing is performed as a preliminary step during enrollment to identify voice prints suitable for text-independent authentication. This automated filtering process maintains efficient enrollment speed while ensuring high authentication performance by pre-qualifying voice prints before they are used for authentication.
3Reliability
If maximum speech duration is increased to improve authentication accuracy, then more speech data is available for analysis, but self-service channel efficiency is reduced and user experience deteriorates
Solution Approach 1:
The system determines maximum speech durations as a function of desired accuracy levels, allowing optimization of the trade-off between authentication accuracy and speech duration. This parameter adjustment enables the system to achieve satisfactory accuracy with minimal speech input, maintaining both reliability and efficiency.
Data Source
AI summary
An interactive voice response (IVR) system comprises a memory storing recorded segments of speech by individuals, and a processor configured to enrol individuals. The enrolment process may comprise retrieving one or more of said recorded segments of speech by an individual from said memory and using the retrieved segments to create a voice print for the individual. The suitability of the voice print for authenticating the individual in an IVR system is then tested. This may be done using segments of speech of a predetermined maximum duration such as three seconds or some other amount commensurate with the typical duration of a voice response in an IVR system. An individual may be enrolled as suitable for IVR authentication if the voice print passed the suitability test. Individuals may be authenticated using a voice print only if the voice print has passed the suitability test.