System and method for automated voice quality testing

• US 9,344,556 B2
• Filed: 05/11/2015
• Issued: 05/17/2016
• Est. Priority Date: 12/22/2009
• Status: Active Grant

• Current Assignee: Cyara Solutions Pty. Ltd.
• Original Assignee: Cyara Solutions Pty. Ltd.
• Inventors: Kulkarni, Alok, Willshire, Geoff
• Primary Examiner(s): Phan, Joseph T
• Application Number:
  US14/709,252
• Publication Number:
  US 20150244857A1
• Time in Patent Office: 372 Days
• Field of Search: 379/32.01
• US Class Current: 1/1
• CPC Class Codes: G10L 25/60 for measuring the quality of voice signals
• CPC Class Codes: H04M 3/2236 Quality of speech transmission monitoring
• CPC Class Codes: H04M 3/323 for the arrangements providing the connection (test connection, test call, call simulation)
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04R 5/027 Spatial or constructional arrangements of microphones, e.g. in dummy heads

Abstract

A system for automated audio quality testing, comprising a plurality of endpoint emulators, call engines, and optionally audio generator devices and head and torso simulator devices, and a method for using such a system for testing of audio quality over a variety of system architectures for optimization of contact center operations and improvement of customer experience.

Claims

1. A system for automated testing of audio quality, comprising:

a call engine comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a computing device, and configured to receive at least a plurality of reference audio samples via a network, and configured to operate at least a simulated telephone call;

an endpoint manager comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a computing device, and configured to provide at least a plurality of reference audio samples to simulate audible responses during a simulated telephonic interaction;

a first audio generator device configured to transmit at least a plurality of reference audio samples; and

a head and torso simulator device comprising at least a microphone and a second audio generator device, and configured to simulate at least a plurality of physical qualities of human head and torso anatomy;

wherein the call engine utilizes a plurality of reference audio samples to simulate inbound telephonic interactions;

wherein the first audio generator device transmits reference audio samples to simulate interaction between a receiving party represented by the head and torso simulator and a plurality of remote calling parties;

wherein the endpoint manager utilizes reference audio samples to simulate telephonic interactions of the receiving party with the plurality of remote calling parties;

wherein the second audio generator device transmits audio from the head and torso simulator device to simulate remote party interaction with the receiving party; and

wherein the first audio generator device transmits audio to the head and torso simulator device to simulate remote party interaction with the receiving party.

3. The system of claim 1, wherein the head and torso simulator device is further configured to simulate a plurality of acoustic properties of human head and torso anatomy.

4. The system of claim 1, wherein the first audio generator device is further configured to produce a plurality of reference audio samples.

5. The system of claim 1, wherein the head and torso simulator device further comprises a plurality of additional microphones.

6. The system of claim 5, wherein at least a portion of the plurality of additional microphones are configured to detect and report background noise.

7. The system of claim 5, wherein the head and torso simulator device further comprises a plurality of additional audio generator devices.

8. The system of claim 7, wherein at least a portion of the plurality of additional audio generator devices is configured to produce a plurality of background noise.

9. The system of claim 8, wherein the head and torso simulator device is further configured to transmit a plurality of audio via at least a portion of the plurality of additional audio generator devices, the plurality of external audio being based at least in part on a plurality of audio being transmitted by a second audio generator device.

10. The system of claim 9, wherein a plurality of additional head and torso simulator devices are configured to simulate audio characteristics of a crowded environment.

11. The system of claim 10, wherein the crowded environment is a contact center, wherein each head and torso simulator device is configured to simulate a contact center agent.

2. A method for automated testing of audio quality, comprising the steps of:

creating, using a call engine comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a computing device, and configured to receive at least a plurality of reference audio samples via a network, and configured to operate at least a simulated telephone call, a simulated call over an audio connection;

receiving a plurality of reference audio at an endpoint manager comprising at least a plurality of programming instructions stored in a memory and operating on a processor of a computing device, and configured to provide at least a plurality of reference audio samples to simulate audible responses during a simulated telephonic interaction and a call engine;

transmitting a plurality of reference audio from the call engine to the endpoint manager;

scoring received reference audio by the endpoint manager;

transmitting a plurality of reference audio from the endpoint manager to the call engine;

scoring received reference audio by the call engine;

scoring the audio connection quality; and

storing audio scoring and audio connection quality data in a database or other data storage medium;

wherein a head and torso simulator device comprising at least a microphone and an audio generator simulates a plurality of properties of a human body and is configured to receive at least a plurality of reference audio transmitted by the call engine and is further configured to transmit the endpoint manager audio.

12. The method of claim 2, further wherein the head and torso simulator device is configured to report on a plurality of background noise.

13. The method of claim 12, further comprising the step of scoring the received background noise.