Context based identification of non-relevant verbal communications

• US 10,678,501 B2
• Filed: 11/12/2019
• Issued: 06/09/2020
• Est. Priority Date: 05/22/2017
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated (Kyndryl Holdings, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Abuelsaad, Tamer E., Boss, Gregory J., Moore, Jr., John E., Rendahl, Randy A.
• Primary Examiner(s): Le, Thuykhanh
• Application Number:
  US16/681,140
• Publication Number:
  US 20200081685A1
• Time in Patent Office: 210 Days
• Field of Search: None
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/0272 Voice signal separating
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 3/568 audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30
• CPC Class Codes: H04M 3/569 using the instant speaker's algorithm speech detection per se G10L25/78

Abstract

A computer-implemented method includes identifying a first set of utterances from a plurality of utterances. The plurality of utterances is associated with a conversation and transmitted via a plurality of audio signals. The computer-implemented method further includes mining the first set of utterances for a first context. The computer-implemented method further includes determining that the first context associated with the first set of utterances is not relevant to a second context associated with the conversation. The computer-implemented method further includes dynamically muting, for at least a first period of time, a first audio signal in the plurality of audio signals corresponding to the first set of utterances. A corresponding computer system and computer program product are also disclosed.

Claims

1. A computer-implemented method comprising:

receiving, by one or more processors, a plurality of audio signals transmitted via a plurality of devices linked by a Voice over Internet Protocol telecommunication network;

identifying, by one or more processors, a plurality of utterances transmitted via the plurality of audio signals;

determining, by one or more processors, a current topic of conversation associated with the plurality of utterances transmitted via the plurality of audio signals;

identifying, by one or more processors, an identity of a speaker associated with a first device transmitting a first audio signal in the plurality of audio signals;

determining, by one or more processors, based on the identity of the speaker, a likelihood that the first audio signal includes a set of utterances that are irrelevant to the current topic of conversation; and

lowering, by one or more processor, a volume of the audio signal transmitted by the first device based, at least in part, on the likelihood that the first audio signal includes utterances that are irrelevant to the current topic of conversation.

2. The computer-implemented method of claim 1, further comprising:

determining, by one or more processors, a first topic associated with a first set of utterances transmitted by the first device via the first audio signal;

determining, by one or more processors, that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances; and

muting, by one or more processors, the first audio signal based, at least in part, on determining that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances.

3. The computer-implemented method of claim 2, further comprising:

monitoring, by one or more processors, a second set of utterances transmitted via the first device while the first audio signal is muted;

determining, by one or more processors, that a second topic associated with the second set of utterances is relevant to the current topic of conversation; and

unmuting, by one or more processors, the first audio signal based, at least in part, on determining that the topic associated with the second set of utterances is relevant to the current topic of conversation.

4. The computer-implemented method of claim 2, further comprising:

generating, by one or more processors, a transcript of the first set of utterances corresponding to the first audio signal that is muted; and

presenting, by one or more processors, the transcript in conjunction with the conversation.

5. The computer-implemented method of claim 2, further comprising:

transmitting, by one or more processors, a notification that the first audio signal is muted.

6. The computer-implemented method of claim 1, further comprising:

identifying, by one or more processors, a location from which a second device is transmitting a second audio signal in the plurality of audio signals;

determining, by one or more processors, based on the location, a likelihood that the second audio signal in the plurality of audio signals includes utterances that are irrelevant to the current topic of conversation; and

lowering, by one or more processors, a volume of the second audio signal transmitted by the second device based, at least in part, on the likelihood that the second audio signal includes utterances that are irrelevant to the current topic of conversation.

7. The computer-implemented method of claim 1, further comprising:

buffering, by one or more processors, for an initial period of time, the plurality of utterances transmitted via the plurality of audio signals; and

redacting, by one or more processors, the first set of utterances prior to being transmitted via the first audio signal corresponding to the first set of utterances.

8. A computer program product, the computer program product comprising one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising instructions to:

receive a plurality of audio signals transmitted via a plurality of devices linked by a Voice over Internet Protocol telecommunication network;

identify a plurality of utterances transmitted via the plurality of audio signals;

determine a current topic of conversation associated with the plurality of utterances transmitted via the plurality of audio signals;

identify an identity of a speaker associated with a first device transmitting a first audio signal in the plurality of audio signals;

determine, based on the identity of the speaker, a likelihood that the first audio signal includes a set of utterances that are irrelevant to the current topic of conversation; and

lower a volume of the audio signal transmitted by the first device based, at least in part, on the likelihood that the first audio signal includes utterances that are irrelevant to the current topic of conversation.

9. The computer program product of claim 8, further comprising instructions to:

determine a first topic associated with a first set of utterances transmitted by the first device via the first audio signal;

determine that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances; and

mute the first audio signal based, at least in part, on determining that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances.

10. The computer program product of claim 9, further comprising instructions to:

monitor a second set of utterances transmitted via the first device while the first audio signal is muted;

determine that a second topic associated with the second set of utterances is relevant to the current topic of conversation; and

unmute the first audio signal based, at least in part, on determining that the topic associated with the second set of utterances is relevant to the current topic of conversation.

11. The computer program product of claim 9, further comprising instructions to:

generate a transcript of the first set of utterances corresponding to the first audio signal that is muted; and

present the transcript in conjunction with the conversation.

12. The computer program product of claim 9, further comprising instructions to:

transmit a notification that the first audio signal is muted.

13. The computer program product of claim 8, further comprising instructions to:

identify a location from which a second device is transmitting a second audio signal in the plurality of audio signals;

determine, based on the location, a likelihood that the second audio signal in the plurality of audio signals includes utterances that are irrelevant to the current topic of conversation; and

lower a volume of the second audio signal transmitted by the second device based, at least in part, on the likelihood that the second audio signal includes utterances that are irrelevant to the current topic of conversation.

14. The computer program product of claim 8, further comprising instructions to:

buffer, for an initial period of time, the plurality of utterances transmitted via the plurality of audio signals; and

redact the first set of utterances prior to being transmitted via the first audio signal corresponding to the first set of utterances.

15. A computer system, the computer system comprising:

one or more computer processors;

one or more computer readable storage media;

computer program instructions;

the computer program instructions being stored on the one or more computer readable storage media for execution by the one or more computer processors; and

the computer program instructions comprising instructions to;

receive a plurality of audio signals transmitted via a plurality of devices linked by a Voice over Internet Protocol telecommunication network;

identify a plurality of utterances transmitted via the plurality of audio signals;

determine a current topic of conversation associated with the plurality of utterances transmitted via the plurality of audio signals;

identify an identity of a speaker associated with a first device transmitting a first audio signal in the plurality of audio signals;

determine, based on the identity of the speaker, a likelihood that the first audio signal includes a set of utterances that are irrelevant to the current topic of conversation; and

lower a volume of the audio signal transmitted by the first device based, at least in part, on the likelihood that the first audio signal includes utterances that are irrelevant to the current topic of conversation.

16. The computer system of claim 15, further comprising instructions to:

determine a first topic associated with a first set of utterances transmitted by the first device via the first audio signal;

determine that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances; and

mute the first audio signal based, at least in part, on determining that the first topic associated with the first set of utterances is irrelevant to the current topic of conversation associated with the plurality of utterances.

17. The computer system of claim 16, further comprising instructions to:

monitor a second set of utterances transmitted via the first device while the first audio signal is muted;

determine that a second topic associated with the second set of utterances is relevant to the current topic of conversation; and

unmute the first audio signal based, at least in part, on determining that the topic associated with the second set of utterances is relevant to the current topic of conversation.

18. The computer system of claim 16, further comprising instructions to:

generate a transcript of the first set of utterances corresponding to the first audio signal that is muted; and

present the transcript in conjunction with the conversation.

19. The computer system of claim 16, further comprising instructions to:

transmit a notification that the first audio signal is muted.

20. The computer system of claim 15, further comprising instructions to:

identify a location from which a second device is transmitting a second audio signal in the plurality of audio signals;

determine, based on the location, a likelihood that the second audio signal in the plurality of audio signals includes utterances that are irrelevant to the current topic of conversation; and

lower a volume of the second audio signal transmitted by the second device based, at least in part, on the likelihood that the second audio signal includes utterances that are irrelevant to the current topic of conversation.