Voice communication management

• US 9,253,304 B2
• Filed: 12/07/2010
• Issued: 02/02/2016
• Est. Priority Date: 12/07/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhogal, Kulvir S., Hollinger, Michael C., King, Jennifer E., Lauridsen, Christina K., Peterson, Robert R.
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): KOVACEK, DAVID M
• Application Number:
  US12/962,111
• Publication Number:
  US 20120143596A1
• Time in Patent Office: 1,883 Days
• Field of Search: 704/1, 704/3, 704/4, 704/8, 704/9, 704/10, 704/200, 704/201, 704/206, 704231-255, 704/258, 704/260, 704270-272, 704/274, 704E15001-E1505, 379/52, 379156-166
• US Class Current: 1/1
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34
• CPC Class Codes: G10L 25/03 characterised by the type of extracted parameters
• CPC Class Codes: H04M 1/72403 with means for local support of applications that increase the functionality
• CPC Class Codes: H04M 2250/74 with voice recognition means

Abstract

A method, a computer program product, and an apparatus for managing a voice communication are provided. In one illustrative embodiment, an audio phrase produced by a first user is identified in the voice communication between the first user and a second user. A determination is made whether the audio phrase is present in a policy which prohibits the transmission of the set of undesired audio phrases. Responsive to a determination that the audio phrase is present in the policy which prohibits the transmission of the set of undesired audio phrases, a communication of the audio phrase is modified.

Claims

1. A method for managing a voice communication, the method comprising:

identifying, by a mobile voice communication device associated with a first user, an audio phrase produced by the first user during the voice communication between the first user using the mobile voice communication device and a second user using another voice communication device;

generating, by the mobile voice communication device associated with the first user, an audio signature of the audio phrase produced by the first user, wherein the audio signature is one or more values generated by performing one or more calculations on an audio segment including the audio phrase;

comparing, by the mobile voice communication device associated with the first user, the audio signature of the audio phrase produced by the first user to audio signatures corresponding to a set of undesirable audio phrases containing confidential information associated with the first user included within a policy prohibiting a transmission of the set of undesired audio phrases;

determining, by the mobile voice communication device associated with the first user, that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases, wherein the matches the audio signature of the undesirable audio phrase in the set of undesirable audio phrases means either a same or a similar audio signature to the audio signatures corresponding to the set of undesirable audio phrases;

responsive to the mobile voice communication device associated with the first user determining that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases, outputting, by the mobile voice communication device associated with the first user, a textual alert message to the first user via a display of the mobile voice communication device associated with the first user that includes a textual representation of the confidential information disclosed and that the confidential information is not to be divulged;

inhibiting, by the mobile voice communication device associated with the first user, the transmission of the undesirable audio phase containing the confidential information from the mobile voice communication device associated with the first user to the other voice communication device used by the second user during the voice communication; and

inhibiting, by the mobile voice communication device associated with the first user, further transmission of audio from the mobile voice communication device associated with the first user to the other voice communication device used by the second user for a period of time until a third user that is a trusted party of the first user joins the voice communication to determine whether the second user is an unauthorized party attempting to fraudulently receive the confidential information from the first user.

2. The method of claim 1, wherein the step of identifying the audio phrase produced by the first user in the voice communication comprises:

generating, by the mobile voice communication device associated with the first user, text that corresponds to a plurality of words in the audio phrase using a speech-to-text process.

3. The method of claim 1, wherein the set of undesired audio phrases in the policy are stored in textual form.

4. The method of claim 1, wherein the audio phrase is a first audio phrase and further comprising:

receiving, by the mobile voice communication device associated with the first user, audio data for a second audio phrase; and

storing, by the mobile voice communication device associated with the first user, the audio data in the policy, which prohibits the transmission of the set of undesired audio phrases as the second audio phrase.

5. The method of claim 4 further comprising:

determining, by the mobile voice communication device associated with the first user, whether the second audio phrase matches the first audio phrase in the policy, which prohibits the transmission of the set of undesired audio phrases.

6. The method of claim 1, wherein the audio phrase is a first audio phrase and further comprising:

receiving, by the mobile voice communication device associated with the first user, a collection of text;

generating, by the mobile voice communication device associated with the first user, audio data for the collection of text using a text-to-speech process; and

storing, by the mobile voice communication device associated with the first user, the audio data in the policy, which prohibits the transmission of the set of undesired audio phrases as a second audio phrase.

7. The method of claim 1, wherein the inhibiting, by the mobile voice communication device associated with the first user, of the transmission of the undesirable audio phrase further comprises:

generating, by the mobile voice communication device associated with the first user, a request for the third user to join the voice communication; and

responsive to the mobile voice communication device associated with the first user sending the request for the third user to join the voice communication, adding, by the mobile voice communication device associated with the first user, the third user to the voice communication.

8. The method of claim 7, wherein the generating, by the mobile voice communication device associated with the first user, the request for the third user to join the voice communication further comprises:

generating, by the mobile voice communication device associated with the first user, an audio alert in the voice communication for the first user and the second user indicating that the third user is being requested to join the voice communication; and

sending, by the mobile voice communication device associated with the first user, the request to the third user with caller identification information corresponding to the second user.

9. The method of claim 8, wherein the audio alert is audible to the first user and inaudible to the second user.

10. The method of claim 1, wherein the voice communication is a telephone call.

11. The method of claim 1, wherein the inhibiting, by the mobile voice communication device associated with the first user, of the transmission of the undesirable audio phrase further comprises:

outputting, by the mobile voice communication device associated with the first user, an audio alert message audible to the first user and inaudible to the second user that the confidential information has been disclosed.

12. The method of claim 1, wherein the second user is the unauthorized party attempting to fraudulently receive the confidential information from the first user to perform unauthorized activities on behalf of the first user using the confidential information without consent of the first user.

13. The method of claim 1, wherein the inhibiting, by the mobile voice communication device associated with the first user, of the transmission of the undesirable audio phrase further comprises:

generating, by the mobile voice communication device associated with the first user, an electronic communication to the third user, wherein the electronic communication is a text message sent to a mobile communication device associated with the third user.

14. The method of claim 13, wherein the inhibiting, by the mobile voice communication device associated with the first user, of the transmission of the undesirable audio phrase further comprises:

generating, by the mobile voice communication device associated with the first user, a request to a fourth user in response to the third user being unavailable.

15. A computer program product stored on a non-transitory computer readable storage medium having program code embodied thereon that is executable by a mobile voice communication data processing system for managing a voice communication, the computer program product comprising:

program code for identifying an audio phrase produced by a first user during the voice communication between the first user using the mobile voice communication data processing system and a second user using another voice communication data processing system;

program code for generating an audio signature of the audio phrase produced by the first user, wherein the audio signature is one or more values generated by performing one or more calculations on an audio segment including the audio phrase;

program code for comparing the audio signature of the audio phrase produced by the first user to audio signatures corresponding to a set of undesirable audio phrases containing confidential information associated with the first user included within a policy prohibiting a transmission of the set of undesired audio phrases;

program code for determining that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases, wherein the matches the audio signature of the undesirable audio phrase in the set of undesirable audio phrases means either same or similar audio signature to the audio signatures corresponding to the set of undesirable audio phrases;

program code, responsive to determining that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases, for outputting a textual alert message to the first user via a display of the mobile voice communication data processing system used by the first user that includes a textual representation of the confidential information disclosed and that the confidential information is not to be divulged;

program code for inhibiting the transmission of the undesirable audio phase containing the confidential information from the mobile voice communication data processing system used by the first user to the other voice communication data processing system used by the second user during the voice communication; and

program code for inhibiting further transmission of audio from the mobile voice communication data processing system used by the first user to the other voice communication data processing system used by the second user for a period of time until a third user that is a trusted party of the first user joins the voice communication to determine whether the second user is an unauthorized party attempting to fraudulently receive the confidential information from the first user.

16. The computer program product of claim 15, wherein the non-transitory computer readable storage medium is in the mobile voice communication data processing system, and the program code is downloaded over a network from a remote data processing system to the non-transitory computer readable storage medium in the mobile voice communication data processing system.

17. The computer program product of claim 16, wherein the remote data processing system is a server data processing system.

18. A mobile voice communication data processing system for managing a voice communication, the mobile voice communication data processing system comprising:

a bus system;

a storage device connected to the bus system, wherein the storage device includes program code; and

a processor unit connected to the bus system, wherein the processing unit executes the program code to;

identify an audio phrase produced by a first user during the voice communication between the first user using the mobile voice communication data processing system and a second user using another voice communication data processing system;

generate an audio signature of the audio phrase produced by the first user, wherein the audio signature is one or more values generated by performing one or more calculations on an audio segment including the audio phrase;

compare the audio signature of the audio phrase produced by the first user to audio signatures corresponding to a set of undesirable audio phrases containing confidential information associated with the first user included within a policy prohibiting a transmission of the set of undesired audio phrases;

determine that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases, wherein the matches the audio signature of the undesirable audio phrase in the set of undesirable audio phrases means either a same or a similar audio signature to the audio signatures corresponding to the set of undesirable audio phrases;

output a textual alert message to the first user via a display of the mobile voice communication data processing system that includes a textual representation of the confidential information disclosed and that the confidential information is not to be divulged in response to determining that the audio signature of the audio phrase produced by the first user matches an audio signature of an undesirable audio phrase in the set of undesirable audio phrases;

inhibit the transmission of the undesirable audio phase containing the confidential information from the mobile voice communication data processing system used by the first user to the other voice communication data processing system used by the second user during the voice communication; and

inhibit further transmission of audio from the mobile voice communication data processing system used by the first user to the other voice communication data processing system used by the second user for a period of time until a third user that is a trusted party of the first user joins the voice communication to determine whether the second user is an unauthorized party attempting to fraudulently receive the confidential information from the first user.