Voice Biometric Caller Identification for Shared Lines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional call set-up processes cannot accurately identify the caller when multiple parties share a single phone line, as they rely on lookup databases and do not provide certainty about the calling party's identity.
Innovation Solution
The integration of Automatic Speech Recognition (ASR) and Voice Biometrics to identify the caller by recognizing their voiceprint, allowing for accurate determination and display of the caller's name during a call, even in shared line scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional lookup database (TCAP) is used to determine Calling Name, then the call set-up process is simple and fast, but the caller identification accuracy deteriorates when multiple parties share a single phone line
Solution Approach 1:
The patent segments the call set-up process into two distinct phases: initial call setup using conventional TCAP lookup for speed, and subsequent biometric verification phase for accurate identification. This segmentation allows the system to maintain simplicity in the primary path while adding complexity only when needed for shared line scenarios.
Solution Approach 2:
The patent introduces voice biometric analysis as an intermediary layer between the caller and the call set-up process. The biometric system acts as a mediator that verifies the actual caller identity by analyzing voice characteristics, bridging the gap between the phone number-based TCAP lookup and the actual human caller.
2Measurement precision
If voice biometrics and ASR are integrated into the call set-up process, then caller identification accuracy is improved, but the processing time and system complexity increase
Solution Approach 1:
The patent performs preliminary voice biometric analysis during the call setup phase, before the actual conversation begins. By extracting and analyzing voice characteristics early in the interaction, the system establishes caller identity upfront, preventing later delays or interruptions for verification.
Solution Approach 2:
The patent replaces the mechanical database lookup system with a biometric recognition system that analyzes voice signals. This substitution transitions from a static, number-based identification mechanism to a dynamic, physiology-based recognition system that can accurately identify callers even when multiple parties share the same phone line.
3Reliability
If biometric authentication is required for all calls, then caller identification reliability is improved, but the ease of operation deteriorates
Solution Approach 1:
The patent implements self-service biometric authentication where the caller's voice is automatically captured and analyzed without requiring manual intervention. The system passively extracts voice characteristics during normal speech and automatically performs biometric verification, eliminating the need for callers to consciously initiate or complete separate authentication steps.
Solution Approach 2:
The patent applies biometric verification selectively rather than universally - only when shared line detection is triggered or when identification reliability is questionable. This partial application of biometric authentication maintains ease of operation for standard calls while ensuring reliability for ambiguous cases.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables precise identification of the caller within a residential or shared line environment, enhancing call management by providing the correct caller name and allowing for customizable call handling and suppression settings based on individual biometric authentication.
Implementation Method 1
automatic discovery, via Automatic Speech Recognition (ASR) and Voice Biometrics, of the identification of a caller
Implementation Method 2
The caller may, for example, initiate a phone call by voice request to a computer or other device
Data Source
AI summary
An embodiment according to the invention provides automatic discovery, via Automatic Speech Recognition (ASR) and Voice Biometrics, of the identification of a caller, when the caller is making a phone call from, for example, a residential line. The caller may, for example, initiate a phone call by voice request to a computer or other device. The device initiates the call, but rather than using the conventional technique of determining Calling Name via lookup to the Transaction Capabilities Application Part (TCAP) database, the embodiment uses a technique of ASR in tandem with voice or other biometrics to recognize who within the residence is making the call, and to use the name associated with the requesting caller's voiceprint for determining the Calling Name to display to the called party. Other forms of biometrics, such as image biometrics (e.g., facial or iris biometrics), may alternatively be employed.