# US 12,120,262 B2 · Voice analysis platform for voiceprint tracking and anomaly detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,120,262 B2
- Document ID: US12120262B2
- Status: Granted
- Kind: B2
- Application number: 17/954,422
- Filed: 2022-09-28
- Published: 2023-01-19
- Granted: 2024-10-15
- Earliest claimed: 2020-11-23
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: George Albero; Youshika C. Scott; Brian H. Corr; Thomas G. Frost; Scott Nielsen; Charlene L. Ramsue
- Web page: https://patentgrep.com/patent/US12120262B2

## CPC

- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- H04M 3/2281: {Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls}
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06Q 20/108: {Remote banking, e.g. home banking}
- G06Q 20/305: {using wired telephone networks}
- G06Q 20/384: {using social networks}
- G06Q 20/40145: {Biometric identity checks}
- G06Q 20/4015: {using location information}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 20/405: {Establishing or using transaction specific rules}
- G10L 17/04: Training, enrolment or model building
- G10L 17/06: Decision making techniques; Pattern matching strategies
- G10L 25/90: Pitch determination of speech signals
- H04M 3/42042: {Notifying the called party of information on the calling party (details within substation equipment H04M1/57, signalling details H04Q3/72)}
- H04M 3/5175: {Call or contact centers supervision arrangements}
- H04M 3/5183: {Call or contact centers with computer-telephony arrangements}
- G10L 17/00: Speaker identification or verification techniques
- H04M 2201/41: using speaker recognition
- H04M 2203/6054: Biometric subscriber identification
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Aspects of the disclosure relate to voiceprint tracking and anomaly detection. A computing platform may detect voice information from a call management system. The computing platform may establish voiceprints for employees and clients of an enterprise. The computing platform may detect a call between an employee and a caller attempting to access a client account. The computing platform may identify a first voiceprint corresponding to the employee and a second voiceprint corresponding to the caller. The computing platform may compare the second voiceprint to a known voiceprint corresponding to the client. Based on the comparison of the second voiceprint to the known voiceprint, the computing platform may determine that the second voiceprint does not match the known voiceprint. The computing platform may identify that the second voiceprint corresponds to another employee of the enterprise, and may send a security notification indicating potential unauthorized account access to an enterprise computing device.

## Claims

### Claim 1

A computing platform comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
establish voiceprints for one or more employees and one or more clients of an enterprise organization corresponding to a call management system;
monitor the call management system to detect a voice call session between an employee and a caller attempting to access an account linked to a client;
identify, based on the voice call session, a first voiceprint corresponding to the employee and a second voiceprint corresponding to the caller;
compare the first voiceprint corresponding to the employee to a known voiceprint corresponding to the employee;
detect voice anomalies corresponding to the employee, wherein detecting the voice anomalies comprises:
determining, by comparing a speech pattern of the first voiceprint corresponding to the employee with a speech pattern of the known voiceprint corresponding to the employee, that the first voiceprint corresponding to the employee does not match the known voiceprint corresponding to the employee, and
identifying that the first voiceprint corresponding to the employee does not match one of the voiceprints for the one or more employees of the enterprise organization; and
send, to an enterprise computing device, a security notification indicating potential unauthorized account access and one or more commands directing the enterprise computing device to display the security notification, wherein sending the one or more commands directing the enterprise computing device to display the security notification causes the enterprise computing device to display the security notification.

### Claim 2 (depends on 1)

The computing platform of claim 1, wherein establishing the voiceprints for the one or more employees and the voiceprints for the one or more clients is based on one or more of: a pitch, a tone, a stutter, a rate of speech, a speech pattern, or an intonation included in subsets of voice information corresponding to each of the one or more employees and the one or more clients.

### Claim 3 (depends on 1)

The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
compare the second voiceprint corresponding to the caller to a known voiceprint corresponding to the client;
determine, based on the comparison of the second voiceprint corresponding to the caller to the known voiceprint corresponding to the client, that the second voiceprint corresponding to the caller does not match the known voiceprint corresponding to the client; and
identify, based on the second voiceprint corresponding to the caller, that the second voiceprint corresponding to the caller corresponds to another employee of the enterprise organization.

### Claim 4 (depends on 3)

The computing platform of claim 3, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
in response to identifying that the second voiceprint corresponding to the caller corresponds to the other employee of the enterprise organization, initiate a claim against the other employee.

### Claim 5 (depends on 3)

The computing platform of claim 3, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
in response to identifying that the second voiceprint corresponding to the caller corresponds to the other employee of the enterprise organization, revoke enterprise permissions corresponding to the other employee.

### Claim 6 (depends on 3)

The computing platform of claim 3, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
identify an additional voice call session that corresponds to the second voiceprint;
identify additional voiceprints corresponding to the additional voice call session; and
store linkage information linking the second voiceprint to the additional voiceprints.

### Claim 7 (depends on 6)

The computing platform of claim 6, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
monitor the call management system to detect additional voice call sessions corresponding to the additional voiceprints; and
flag requests corresponding to the additional voice call sessions as suspicious.

### Claim 8 (depends on 7)

The computing platform of claim 7, wherein the employee corresponds a first location of the enterprise organization, and wherein the additional voice call sessions correspond to other locations, different than the first location, of the enterprise organization.

### Claim 9 (depends on 3)

The computing platform of claim 3, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
identify transactions processed by the other employee; and
flag the identified transactions for further review.

### Claim 10 (depends on 1)

The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
compare the first voiceprint corresponding to the employee to a known voiceprint corresponding to the employee; and
detect voice anomalies corresponding to the employee, wherein detecting the voice anomalies comprises:
determining, based on the comparison of the first voiceprint corresponding to the employee to the known voiceprint corresponding to the employee, that the first voiceprint corresponding to the employee does not match the known voiceprint corresponding to the employee, and
identifying that the first voiceprint corresponding to the employee does not match one of the voiceprints for the one or more employees of the enterprise organization.

### Claim 11 (depends on 10)

The computing platform of claim 10, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
in response to detecting the voice anomalies:
revoking enterprise permissions corresponding to the employee, and
prompting for re-authentication by the employee to re-instate the revoked enterprise permissions.

### Claim 12 (depends on 1)

The computing platform of claim 1, wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
detect voice information from the call management system, wherein the voiceprints for the one or more employees and the one or more clients of the enterprise organization are based on the voice information.

### Claim 13

A method comprising:
at a computing platform comprising at least one processor, a communication interface, and memory:
establishing voiceprints for one or more employees and one or more clients of an enterprise organization corresponding to a call management system;
monitoring the call management system to detect a voice call session between an employee and a caller attempting to access an account linked to a client;
identifying, based on the voice call session, a first voiceprint corresponding to the employee and a second voiceprint corresponding to the caller;
comparing the first voiceprint corresponding to the employee to a known voiceprint corresponding to the employee;
detecting voice anomalies corresponding to the employee, wherein detecting the voice anomalies comprises:
determining, by comparing a speech pattern of the first voiceprint corresponding to the employee with a speech pattern of the known voiceprint corresponding to the employee, that the first voiceprint corresponding to the employee does not match the known voiceprint corresponding to the employee, and
identifying that the first voiceprint corresponding to the employee does not match one of the voiceprints for the one or more employees of the enterprise organization; and
sending, to an enterprise computing device, a security notification indicating potential unauthorized account access and one or more commands directing the enterprise computing device to display the security notification, wherein sending the one or more commands directing the enterprise computing device to display the security notification causes the enterprise computing device to display the security notification.

### Claim 14 (depends on 13)

The method of claim 13, wherein establishing the voiceprints for the one or more employees and the voiceprints for the one or more clients is based on one or more of: a pitch, a tone, a stutter, a rate of speech, a speech pattern, or an intonation included in subsets of voice information corresponding to each of the one or more employees and the one or more clients.

### Claim 15 (depends on 13)

The method of claim 13, further comprising:
comparing the second voiceprint corresponding to the caller to a known voiceprint corresponding to the client;
determining, based on the comparison of the second voiceprint corresponding to the caller to the known voiceprint corresponding to the client, that the second voiceprint corresponding to the caller does not match the known voiceprint corresponding to the client; and
identifying, based on the second voiceprint corresponding to the caller, that the second voiceprint corresponding to the caller corresponds to another employee of the enterprise organization.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
in response to identifying that the second voiceprint corresponding to the caller corresponds to the other employee of the enterprise organization, initiating a claim against the other employee.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
in response to identifying that the second voiceprint corresponding to the caller corresponds to the other employee of the enterprise organization, revoking enterprise permissions corresponding to the other employee.

### Claim 18 (depends on 15)

The method of claim 15, further comprising:
identifying an additional voice call session that corresponds to the second voiceprint;
identifying additional voiceprints corresponding to the additional voice call session; and
storing linkage information linking the second voiceprint to the additional voiceprints.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
monitoring the call management system to detect additional voice call sessions corresponding to the additional voiceprints; and
flagging requests corresponding to the additional voice call sessions as suspicious.

### Claim 20

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:
establish voiceprints for one or more employees and one or more clients of an enterprise organization corresponding to a call management system;
monitor the call management system to detect a voice call session between an employee and a caller attempting to access an account linked to a client;
identify, based on the voice call session, a first voiceprint corresponding to the employee and a second voiceprint corresponding to the caller;
compare the first voiceprint corresponding to the employee to a known voiceprint corresponding to the employee;
detect voice anomalies corresponding to the employee, wherein detecting the voice anomalies comprises:
determining, by comparing a speech pattern of the first voiceprint corresponding to the employee with a speech pattern of the known voiceprint corresponding to the employee, that the first voiceprint corresponding to the employee does not match the known voiceprint corresponding to the employee, and
identifying that the first voiceprint corresponding to the employee does not match one of the voiceprints for the one or more employees of the enterprise organization; and
send, to an enterprise computing device, a security notification indicating potential unauthorized account access and one or more commands directing the enterprise computing device to display the security notification, wherein sending the one or more commands directing the enterprise computing device to display the security notification causes the enterprise computing device to display the security notification.