# US 2017/0257482 A1 · System and method for reliable call recording testing and proprietary customer information retrieval

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

- Number: US 2017/0257482 A1
- Document ID: US20170257482A1
- Status: Published application
- Kind: A1
- Application number: 15/468,104
- Filed: 2017-03-23
- Published: 2017-09-07
- Earliest claimed: 2014-09-09
- Assignees: Cyara Solutions Pty Ltd
- Applicants: Cyara Solutions Pty Ltd
- Inventors: Brian Chapman; Geoff Willshire
- Web page: https://patentgrep.com/patent/US20170257482A1

## CPC

- H04M 3/28: Automatic routine testing {; Fault testing; Installation testing; Test methods, test equipment or test arrangements therefor}
- G06F 16/683: using metadata automatically derived from the content
- H04M 3/323: {for the arrangements providing the connection (test connection, test call, call simulation)}
- H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)}
- G10L 13/04: Details of speech synthesis systems, e.g. synthesiser structure or memory management
- G10L 25/18: the extracted parameters being spectral information of each sub-band
- G10L 25/51: for comparison or discrimination
- H04M 3/5175: {Call or contact centers supervision arrangements}
- H04M 2201/41: using speaker recognition
- H04M 2203/301: Management of recordings
- H04M 2203/303: Marking
- H04M 2203/558: Databases
- 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)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system and methods for reliable call recording testing and proprietary customer information retrieval, wherein recording may be both active and passive in nature, recording call audio from the moment a call begins such as to include dial tones, IVR interactions, and other non-conversation call contents that may generally be omitted in traditional recordings. These recordings may then be compared to similar recordings collected by traditional systems to “align” the recordings, identifying portions of the call that may have been omitted from one recording by using audio fingerprinting to match recordings up for improved analysis.

## Claims

### Claim 1

A call recording test engine, comprising:
a test database configured to store and provide testing information, the testing information comprising at least a test configuration;
a synthetic call generator configured to produce test voice calls into a contact center, the test voice calls being based at least in part on the test information and comprising at least audio-based voice interaction; and
a test manager configured to retrieve testing information from the test database, direct the operation of the synthetic call generator, record the test voice call, connect to a call recording system operated by a contact center, retrieve a recording from the call recording system, and analyze the retrieved recording based at least in part on the testing information, the analysis comprising at least a comparison between the recorded test voice call and the retrieved call recording.

### Claim 2 (depends on 1)

The system of claim 1, wherein the analysis comprises at least a plurality of audio fingerprinting techniques.

### Claim 3 (depends on 1)

The system of claim 1, wherein the analysis comprises at least a fast Fourier transform algorithmic analysis.

### Claim 4

A method for reliable call recording testing and proprietary customer information retrieval, comprising the steps of:
connecting, using a test manager configured to retrieve testing information from the test database, connect to a call recording system operated by a contact center, retrieve a recording from the call recording system, and analyze the retrieved recording based at least in part on the testing information, to a call recording system operated by a contact center;
placing, using a synthetic call generator configured to produce test voice calls into a contact center, the test voice calls being based at least in part on the test information, a test voice call;
producing an enhanced recording based at least in part on the test voice call;
retrieving a recording from the contact center call recording system; and
comparing the enhanced recording against the retrieved recording.

### Claim 5 (depends on 4)

The method of claim 4, wherein the comparison comprises at least the use of audio fingerprinting.
