System and method for analyzing and classifying calls without transcription

• US 10,348,896 B2
• Filed: 03/31/2017
• Issued: 07/09/2019
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Marchex Incorporated
• Original Assignee: Marchex Incorporated
• Inventors: Kolbegger, Chris, Flaks, Jason, Graber, Tim, Rieger, Bryan, Ismail, Ziad, Ramanathan, Govindaraj, Spehr, Darren, Berk, Matthew
• Primary Examiner(s): Teshale, Akelaw
• Application Number:
  US15/475,456
• Publication Number:
  US 20170366668A1
• Time in Patent Office: 830 Days
• Field of Search: 37926502, 37926507, 37926509, 37926511, 37926512, 37914209, 37920103, 37921001, 37926505, 37926513, 37926514, 37926608, 379 8801
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence
• CPC Class Codes: H04L 41/5067 Customer-centric QoS measurements
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04M 2203/559 Sorting systems
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Claims

1. A method in a computing system for analyzing a telephone call without transcription, the method comprising:

receiving an audio signal of the telephone call, wherein the telephone call includes a first channel and a second channel; and

generating a display based on the received audio signal, the display comprising;

a first portion illustrating the first channel, wherein the illustration of the first channel depicts a first time-in-activity of the telephone call, the depiction of the first time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time;

a second portion illustrating the second channel, wherein the illustration of the second channel depicts a second time-in-activity of the telephone call, the depiction of the second time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time; and

a third portion indicating an outcome of the telephone call, wherein the outcome is identified by analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call.

2. The method of claim 1 wherein the outcome of the telephone call is identified by further determining whether the pattern of interaction occurs in a beginning, middle, or end of the telephone call.

3. The method of claim 1 wherein analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call comprises:

detecting a monologue when there is a predetermined amount of time-in-activity corresponding to speech on only one channel of the at least two channels;

detecting a conversation when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech;

detecting a call silence when there is no first time-in-activity and no second time-in-activity; and

detecting a collision when there is coinciding first time-in-activity and the second time-in-activity.

4. The method of claim 1, wherein the identified outcome of the telephone call indicates:

an Interactive Voice Response when there is a predetermined amount of first time-in-activity corresponding to speech and a relatively insubstantial second time-in-activity corresponding to speech at the beginning of the telephone call;

a wrong number when there is a predetermined amount of first time-in-activity and a relatively insubstantial second time-in-activity at the beginning of the telephone call;

an exchange of client information when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the beginning of the telephone call;

a reading of terms and conditions or a description of products or services when there is a predetermined amount of second time-in-activity corresponding to speech in the middle of the telephone call; and

an end-of-call thrash when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the end of the telephone call.

5. The method of claim 1 wherein the audio signal of the telephone call is a pre-recorded file.

6. The method of claim 1 wherein the audio signal of the telephone call is a live, unrecorded telephone call.

7. The method of claim 1 wherein the non-speech activity is a ring tone, a dual-tone multi-frequency tone (DTMF), or music.

8. A computing system for analyzing a telephone call without transcription, the computing system comprising:

a memory for storing programmed instructions;

a processor configured to execute the programmed instructions to perform operations including;

receiving an audio signal of the telephone call, wherein the telephone call includes a first channel and a second channel;

illustrating the first channel in a first portion of a display, wherein the illustration of the first channel depicts a first time-in-activity of the telephone call, the depiction of the first time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time;

illustrating the second channel in a second portion of the display, wherein the illustration of the second channel depicts a second time-in-activity of the telephone call, the depiction of the second time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time; and

displaying an outcome of the telephone call in a third portion of a display, wherein the outcome is identified by analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call.

9. The computing system claim 8 wherein identifying the outcome of the telephone call is further achieved by:

determining whether the pattern of interaction occurs in a beginning, middle, or end of the telephone call.

10. The computing system of claim 8 wherein analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call comprises:

detecting a monologue when there is a predetermined amount of time-in-activity corresponding to speech on only one channel of the at least two channels;

detecting a conversation when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech;

detecting a call silence when there is no first time-in-activity and no second time-in-activity; and

detecting a collision when there is coinciding first time-in-activity and the second time-in-activity.

11. The computing system of claim 8, wherein the identified outcome of the telephone call indicates:

an Interactive Voice Response when there is a predetermined amount of first time-in-activity corresponding to speech and a relatively insubstantial second time-in-activity corresponding to speech at the beginning of the telephone call;

a wrong number when there is a predetermined amount of first time-in-activity and a relatively insubstantial second time-in-activity at the beginning of the telephone call;

an exchange of client information when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the beginning of the telephone call;

a reading of terms and conditions or a description of products or services when there is a predetermined amount of second time-in-activity corresponding to speech in the middle of the telephone call; and

an end-of-call thrash when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the end of the telephone call.

12. The computing system of claim 8 wherein the audio signal of the telephone call is a pre-recorded file.

13. The computing system of claim 8 wherein the audio signal of the telephone call is a live, unrecorded telephone call.

14. The computing system of claim 8 wherein the non-speech activity is a ring tone, a dual-tone multi-frequency tone (DTMF), or music.

15. A non-transitory computer-readable storage medium with instructions stored thereon that, when executed by a computing system, cause the computing system to perform a method for analyzing a telephone call without transcription, the method comprising:

receiving an audio signal of the telephone call, wherein the telephone call includes a first channel and a second channel;

illustrating the first channel in a first portion of a display, wherein the illustration of the first channel depicts a first time-in-activity of the telephone call, the depiction of the first time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time;

illustrating the second channel in a second portion of the display, wherein the illustration of the second channel depicts a second time-in-activity of the telephone call, the depiction of the second time-in-activity of the telephone call including an identification of speech activity and non-speech activity, the speech activity and non-speech activity being depicted as a function of time; and

displaying an outcome of the telephone call in a third portion of the display, wherein the outcome is identified by analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call.

16. The non-transitory computer-readable storage medium of claim 15 wherein identifying the outcome of the telephone call is further achieved by:

determining whether the pattern of interaction occurs in a beginning, middle, or end of the telephone call.

17. The non-transitory computer-readable storage medium of claim 15 wherein analyzing a pattern of interaction between the first time-in-activity of the telephone call and the second time-in-activity of the telephone call comprises:

detecting a monologue when there is a predetermined amount of time-in-activity corresponding to speech on only one channel of the at least two channels;

detecting a conversation when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech;

detecting a call silence when there is no first time-in-activity and no second time-in-activity; and

detecting a collision when there is coinciding first time-in-activity and the second time-in-activity.

18. The non-transitory computer-readable storage medium of claim 15, wherein the identified outcome of the telephone call indicates:

an Interactive Voice Response when there is a predetermined amount of first time-in-activity corresponding to speech and a relatively insubstantial second time-in-activity corresponding to speech at the beginning of the telephone call;

a wrong number when there is a predetermined amount of first time-in-activity and a relatively insubstantial second time-in-activity at the beginning of the telephone call;

an exchange of client information when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the beginning of the telephone call;

a reading of terms and conditions or a description of products or services when there is a predetermined amount of second time-in-activity corresponding to speech in the middle of the telephone call; and

an end-of-call thrash when there is a predetermined rate of interchange between the first time-in-activity corresponding to speech and the second time-in-activity corresponding to speech at the end of the telephone call.

19. The non-transitory computer-readable storage medium of claim 15 wherein the audio signal of the telephone call is a pre-recorded file.

20. The non-transitory computer-readable storage medium of claim 15 wherein the audio signal of the telephone call is a live, unrecorded telephone call.