System and Method for Live Voice and Voicemail Detection

• US 20140369479A1
• Filed: 06/12/2013
• Published: 12/18/2014
• Est. Priority Date: 06/12/2013
• Status: Active Grant

• Current Assignee: Nobelbiz Incorporated
• Original Assignee: Nobelbiz Incorporated
• Inventors: Siminoff, James
• Granted Patent: US 9,210,264 B2
• Time in Patent Office: Days
• US Class Current: 379/88.01
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26
• CPC Class Codes: H04M 3/5235 Dependent on call type or called number [DNIS]

Abstract

A computer system for processing audio on a call having a processor in communication with non-volatile memory having code for converting recorded audio into a vector, comparing the recorded audio vector with a plurality of audio vectors and generating a comparative match number for each comparison, identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number, connecting the call to an agent when the closest audio vector is designated as live-voice.

Claims

1. A computer system for processing audio on a call, comprising:

a processor in communication with non-volatile memory, the non-volatile memory comprising;

code for detecting audio on the call;

code for recording audio on the call and converting the recorded audio into a vector;

code for comparing the recorded audio vector with a plurality of audio vectors stored in a database and generating a comparative match number for each comparison, where each of the plurality of audio vectors is designated as live-voice or pre-recorded;

code for identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number;

code for connecting the call to an agent when the closest audio vector is designated as live-voice and storing the recorded audio vector in the database with live-voice designation; and

code storing the recorded audio vector in the database with pre-recorded designation when the closest audio vector is designated as pre-recorded.

2. The system of claim 1, further comprising code for determining no match when a highest comparative match number is below the predetermined threshold value, then using one or more timers to determine whether the recorded audio contains live-voice or pre-recorded audio.

3. The system of claim 2, further comprising code for storing the recorded audio vector in the database with live-voice or pre-recorded designation.

4. The system of claim 1, further comprising code for disconnecting the call when the closest audio vector is designated as pre-recorded.

5. The system of claim 4, further comprising code for playing an audio message on the call before disconnecting the call.

6. The system of claim 1, further comprising code for playing an audio message on the call before connecting the call.

7. The system of claim 1, further comprising code for storing call information in the database and associating the call information with the recorded audio vector.

8. The system of claim 7, wherein the call information comprises at least one of calling party phone number, called party phone number, call start time, call end time, call duration, language spoken, and charges.

9. The system of claim 7, wherein the code for identifying the closest audio vector uses stored call information.

10. A computer system for processing audio on a call, comprising:

a processor in communication with non-volatile memory, the non-volatile memory comprising;

an audio detection system in electrical communication with a database, the audio detection system capable of

detecting audio on the call;

recording audio on the call;

converting the recorded audio into a vector;

comparing the recorded audio vector with a plurality of audio vectors stored in the database and generating a comparative match number for each comparison, where each of the plurality of audio vectors is designated as live-voice or pre-recorded; and

identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number;

a call distribution system in electrical communication with the audio detection system, the database, and a communication network, the call distribution system capable of placing the call;

connecting the call to an agent when the closest audio vector is designated as live-voice and storing the recorded audio vector in the database with live-voice designation; and

storing the recorded audio vector in the database with pre-recorded designation when the closest audio vector is designated as pre-recorded.

11. The computer system of claim 10, wherein the audio detection system is further capable of determining no match when a highest comparative match number is below the predetermined threshold value, then using one or more timers to determine whether the recorded audio contains live-voice or pre-recorded audio.

12. The computer system of claim 11, wherein the audio detection system is further capable of storing the recorded audio vector in the database with live-voice or pre-recorded designation.

13. The computer system of claim 10, wherein the call distribution system is further capable of disconnecting the call when the closest audio vector is designated as pre-recorded.

14. The computer system of claim 13, wherein the call distribution system is further capable of playing an audio message on the call before disconnecting the call.

15. The computer system of claim 13, wherein the call distribution system is further capable of playing an audio message on the call before connecting the call.

16. The computer system of claim 10, wherein the audio detection system is further capable of storing call information in the database and associating the call information with the recorded audio vector.

17. The computer system of claim 16, wherein the call information comprises at least one of calling party phone number, called party phone number, call start time, call end time, call duration, language spoken, and charges.

18. The computer system of claim 16, wherein the audio detection system is capable of identifying the closest audio vector using stored call information.