SYSTEM AND METHOD FOR CALL PROGRESS DETECTION

• US 20160261743A1
• Filed: 09/04/2015
• Published: 09/08/2016
• Est. Priority Date: 03/02/2015
• Status: Active Grant

• Current Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Grodek, Vera, Mehrotra, Gaurav, Shundo, Nelson, Lee, Alex Ka Yu, Gvildys, Paul
• Granted Patent: US 10,142,471 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/12 using dynamic programming techniques, e.g. dynamic time warping [DTW]
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/24 the extracted parameters being the cepstrum
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 2203/2027 Live party detection
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• 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 3/53308 Message originator indirectly connected to the message centre, e.g. after detection of busy or absent state of a called party

Abstract

A contact center includes an outbound server to make a call to a callee and a media device. The media device receives an audio signal based on the call, to determine a Mel-frequency cepstral coefficient for the received audio signal, and to match the Mel-frequency cepstral coefficient for the audio signal to a Mel-frequency cepstral coefficient for a pre-recorded carrier message. The media device can determine a content of the audio signal based on the match.

Claims

1. A contact center, comprising:

an outbound server device to make a call to a callee;

a media device to receive an audio signal based on the call, to determine a Mel-frequency cepstral coefficient for the received audio signal, and to match the Mel-frequency cepstral coefficient for the audio signal to a Mel-frequency cepstral coefficient for a pre-recorded carrier message; and

the media device to determine a content of the audio signal based on the match.

2. The contact center of claim 1, where the media device matches the audio signal to the pre-recorded carrier message pre-connection to the callee.

3. The contact center of claim 1, where the media device further divides the audio signal into frames of a same size as the pre-recorded carrier message before the match.

4. The contact center of claim 1, where the media device receives the audio signal in real-time.

5. The contact center of claim 1, further comprising a database connected with the media device, the database to store the Mel-frequency cepstral coefficient for the pre-recorded carrier message.

6. The contact center of claim 1, where media device receives the audio signal over a media channel.

7. The contact center of claim 1, where the media device comprises a media control platform.

8. The contact center of claim 1, where the pre-recorded carrier message comprises at least one of a line is busy, a lack of a circuit, a number is no longer in service, and a call is being forwarded to an answering machine.

9. The contact center of claim 1, where the media device further performs a dynamic time warping after the Mel-frequency cepstral coefficient to aid with a comparison of the audio signal with the pre-recorded carrier message.

10. The contact center of claim 1, further comprising the media device dividing a voice input into frames, performing a discrete Fourier transform to compute the fast Fourier transform of each frame to convert each frame of samples from a time domain into a frequency domain to determine a magnitude spectrum of the voice input, performing a filter according to Mel scale to output a log Mel spectrum of the voice input, and applying a discrete Cosine transform to convert the log Mel spectrum into the time domain to determine the Mel-frequency cepstral coefficient of the pre-recorded carrier message.

11. A computer implemented method, comprising:

making an outbound call to a callee;

receiving an audio signal based on the outbound call, to determine a Mel-frequency cepstral coefficient for the received audio signal;

matching the Mel-frequency cepstral coefficient for the audio signal to a Mel-frequency cepstral coefficient for a pre-recorded carrier message; and

determining a content of the audio signal based on the match.

12. The computer implemented method of claim 11, further comprising matching the audio signal to the pre-recorded carrier message pre-connection to the callee.

13. The computer implemented method of claim 12, further comprising continuing with detection post connection if there are no matches.

14. The computer implemented method of claim 11, further comprising dividing the audio signal into frames of a same size as the pre-recorded carrier message before the matching.

15. The computer implemented method of claim 11, further comprising receiving the audio signal in real-time.

16. The computer implemented method of claim 11, further comprising receiving the audio signal over a media channel.

17. The computer implemented method of claim 11, where the pre-recorded carrier message comprises at least one of a line is busy, a lack of a circuit, a number is no longer in service, and a call is being forwarded to an answering machine.

18. The computer implemented method of claim 11, further comprising dynamic time warping after the Mel-frequency cepstral coefficient to aid with a comparison of the audio signal with the pre-recorded carrier message.

19. The computer implemented method of claim 11, further comprising the dividing a voice input into frames;

performing a discrete Fourier transform to compute the fast Fourier transform of each frame to convert each frame of samples from a time domain into a frequency domain to determine a magnitude spectrum of the voice input;

performing a filter according to Mel scale to output a log Mel spectrum of the voice input; and

applying a discrete Cosine transform to convert the log Mel spectrum into the time domain to determine the Mel-frequency cepstral coefficient of the pre-recorded carrier message.

20. The computer implemented method of claim 11, further comprising storing the Mel-frequency cepstral coefficient for the pre-recorded carrier message in a database.