Call Handling System Using Acoustic Analysis for Spoofed Number Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to effectively classify and handle unwanted telephone calls, particularly those using spoofed numbers, which can lead to fraudulent activities and disrupt legitimate communications.
Innovation Solution
A system and method that intercepts call requests, generates a call recording, determines attributes using an automatic speech recognizer, and classifies calls as unwanted using a trained classifier, allowing for early termination and secure handling of such calls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If call blocking based on number databases is used, then spam call identification is improved, but spoofed number detection fails and legitimate calls are blocked
Solution Approach 1:
The patent replaces the mechanical database-matching system with an acoustic analysis system that examines voice signal characteristics. Instead of relying on number databases that fail against spoofing, the system uses automatic speech recognition and voice biometrics to identify fraudulent calls based on acoustic patterns, thereby maintaining reliability while adapting to spoofed numbers.
Solution Approach 2:
The patent introduces voice signal analysis as an intermediary layer between the caller ID and the blocking decision. This intermediary examines the acoustic characteristics of the voice signal to determine whether a call is fraudulent, even when the number appears legitimate in databases, thus resolving the contradiction between database reliability and spoofing detection.
2Reliability
If all incoming calls are verified against databases, then fraud detection is improved, but call handling speed decreases
Solution Approach 1:
The patent applies partial verification by analyzing only specific acoustic features and voice patterns rather than performing complete database checks on all calls. The system focuses on key indicators of fraud such as voice biometric mismatches and suspicious speech patterns, achieving reliable fraud detection while maintaining fast call handling speeds.
Solution Approach 2:
The patent performs preliminary acoustic analysis of voice signals during call setup before full connection is established. By examining voice characteristics early in the call process, the system can quickly identify fraudulent calls and terminate them before significant resources are consumed, thereby maintaining both high reliability and fast handling speed.
3Object-affected harmful factors
If number spoofing protection is implemented, then fraud prevention is improved, but legitimate calls from spoofed numbers are blocked
Solution Approach 1:
The patent applies local quality analysis by examining specific acoustic characteristics of voice signals rather than making blanket blocking decisions based on number patterns. The system analyzes local features such as voice biometrics, speech patterns, and tonal qualities to distinguish fraudulent calls from legitimate ones, even when numbers are spoofed, thereby preventing fraud while maintaining reliable delivery of legitimate calls.
Solution Approach 2:
The patent changes the verification parameter from static number matching to dynamic acoustic feature analysis. By monitoring voice signal parameters such as frequency, timbre, and speech patterns in real-time, the system can adaptively distinguish between fraudulent and legitimate calls, preventing fraud without blocking legitimate traffic from spoofed numbers.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed herein are systems and methods for handling unwanted telephone calls. In one example, an exemplary method comprises, intercepting a call request for a call from a terminal device of a calling party to a terminal device of a called party, generating a call recording containing media data transmitted within a connection established by the intercepted call request, determining attributes of the generated call recording, classifying the call as an unwanted call based on the determined attributes, wherein the classification is performed by a classifier trained on previously collected unwanted calls, and wherein the call is classified as unwanted when the attributes belong to an unwanted call class that is known, and handling the call in accordance with the classification of the call, the handling including at least securing information of the call.