Monitoring and maintaining signal quality for each participant of a group call

1 . A computer-implemented method (CIM), comprising:

receiving a source audio signal from a speaker on a group call between the speaker and participants;

receiving copies of resulting audio signals from the participants, the copies of the resulting audio signals including unique versions of the source audio signal as received by the respective participants;

determining an amount of the source audio signal received by the respective participants by comparing the source audio signal with the respective copies of the resulting audio signals; and

outputting statuses to the speaker, the statuses being correlated with the amount of the source audio signal received by the respective participants by:

dynamically combining the statuses, correlated with the amount of the source audio signal received by the respective participants, into a summary,

causing the summary to be displayed in real-time on a user interface corresponding to the speaker, and

dynamically updating the summary as the statuses change over time.

2 . The CIM of claim 1 , comprising:

in response to determining the amount of the source audio signal received by a given participant is outside a predetermined range, identifying portions of the source audio signal that are absent from the copy of the resulting audio signal received by the given participant;

resending the identified portions of the source audio signal to the given participant; and

causing the identified portions of the source audio signal to replace corresponding portions of the resulting audio signal received by the given participant.

3 . The CIM of claim 2 , comprising:

causing a logical button to be displayed on a user interface corresponding to the given participant, the logical button being configured to initiate replaying the identified portions of the source audio signal in response to the logical button being activated.

4 . The CIM of claim 1 , wherein the determining of the amount of the source audio signal received by a given participant includes:

producing first sentence segments by performing sentence segmentation on the source audio signal;

partitioning the first sentence segments based at least in part on respective types of statements made in the first sentence segments and/or respective subjects of the statements in the first sentence segments;

using the partitioned first sentence segments to generate a first sentence segmentation dataset for the source audio signal;

producing second sentence segments by performing sentence segmentation on the respective copy of the resulting audio signal received by the given participant, wherein the second sentence segments are not partitioned;

using the non-partitioned second sentence segments to generate a second sentence segmentation dataset for the respective copy of the resulting audio signal received by the given participant; and

comparing the first and second sentence segmentation datasets.

5 . The CIM of claim 1 , wherein the determining of the amount of the source audio signal received by the respective participants includes, for each of the participants:

determining whether one of the copies of the resulting audio signals was received from a given participant;

in response to determining one of the copies of the resulting audio signals was received from the given participant, comparing the source audio signal with the determined one of the copies of the resulting audio signals; and

determining a number of differences between the source audio signal and the determined one of the copies of the resulting audio signals.

6 . The CIM of claim 5 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining one of the copies of the resulting audio signals was not received for the given participant, outputting a negative status for the given participant to the speaker.

7 . The CIM of claim 5 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining the number of differences between the source audio signal and the determined one of the copies of the resulting audio signals is not in a predetermined range, outputting a negative status for the given participant to the speaker.

8 . The CIM of claim 7 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining the number of differences between the source audio signal and the determined one of the copies of the resulting audio signals is in the predetermined range, outputting a positive status for the given participant to the speaker.

9 . A computer program product (CPP), comprising:

a set of one or more computer readable storage media; and

program instructions, collectively stored in the set of one or more storage media, for causing a processor set to perform computer operations including:

receive a source audio signal from a speaker on a group call between the speaker and participants;

receive copies of resulting audio signals from the participants, the copies of the resulting audio signals including unique versions of the source audio signal as received by the respective participants;

determine an amount of the source audio signal received by the respective participants by comparing the source audio signal with the respective copies of the resulting audio signals; and

output statuses to the speaker, the statuses being correlated with the amount of the source audio signal received by the respective participants by:

dynamically combining the statuses, correlated with the amount of the source audio signal received by the respective participants, into a summary,

causing the summary to be displayed in real-time on a user interface corresponding to the speaker, and

dynamically updating the summary as the statuses change over time.

10 . The CPP of claim 9 , comprising program instructions, collectively stored in the set of one or more computer readable storage media, for causing the processor set to perform computer operations further including:

in response to determining the amount of the source audio signal received by a given participant is outside a predetermined range, identify portions of the source audio signal that are absent from the copy of the resulting audio signal received by the given participant;

resend the identified portions of the source audio signal to the given participant; and

cause the identified portions of the source audio signal to replace the corresponding portions of the resulting audio signal received by the given participant.

11 . The CPP of claim 10 , comprising program instructions, collectively stored in the set of one or more computer readable storage media, for causing the processor set to perform computer operations further including:

cause a logical button to be displayed on a user interface corresponding to the given participant, the logical button being configured to initiate replaying the identified portions of the source audio signal in response to the logical button being activated.

12 . The CPP of claim 9 , wherein the determining of the amount of the source audio signal received by a given participant includes:

performing sentence segmentation on the source audio signal;

generating a first sentence segmentation dataset for the source audio signal;

performing sentence segmentation on the respective copy of the resulting audio signal received by the given participant;

generating a second sentence segmentation dataset for the respective copy of the resulting audio signal received by the given participant; and

comparing the first and second datasets.

13 . The CPP of claim 9 , wherein the determining of the amount of the source audio signal received by the respective participants includes, for each of the participants:

determining whether one of the copies of the resulting audio signals was received from a given participant;

in response to determining one of the copies of the resulting audio signals was received from the given participant, comparing the source audio signal with the determined one of the copies of the resulting audio signals; and

determining a number of differences between the source audio signal and the determined one of the copies of the resulting audio signals.

14 . The CPP of claim 13 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining one of the copies of the resulting audio signals was not received for the given participant, outputting a negative status for the given participant to the speaker.

15 . The CPP of claim 13 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining the number of differences between the source audio signal and the determined one of the copies of the resulting audio signals is not in a predetermined range, outputting a negative status for the given participant to the speaker.

16 . The CPP of claim 15 , wherein the determining of the amount of the source audio signal received by the respective participants further includes, for each of the participants:

in response to determining the number of differences between the source audio signal and the determined one of the copies of the resulting audio signals is in the predetermined range, outputting a positive status for the given participant to the speaker.

17 . A computer system (CS), comprising:

a processor set;

a set of one or more computer readable storage media;

program instructions, collectively stored in the set of one or more computer readable storage media, for causing the processor set to perform computer operations including:

receive a source audio signal from a speaker on a group call between the speaker and participants;

receive copies of resulting audio signals from the participants, the copies of the resulting audio signals including unique versions of the source audio signal as received by the respective participants;

determine an amount of the source audio signal received by the respective participants by comparing the source audio signal with the respective copies of the resulting audio signals;

output statuses to the speaker, the statuses being correlated with the amount of the source audio signal received by the respective participants; and

in response to determining the amount of the source audio signal received by a given participant is outside a predetermined range:

identify portions of the source audio signal that are absent from the copy of the resulting audio signal received by the given participant;

resend the identified portions of the source audio signal to the given participant;

cause the identified portions of the source audio signal to replace the corresponding portions of the resulting audio signal received by the given participant; and

cause a logical button to be displayed on a user interface corresponding to the given participant, the logical button being configured to initiate replaying the identified portions of the source audio signal in response to the logical button being activated.

18 . The CS of claim 17 , comprising program instructions, collectively stored in the set of one or more computer readable storage media, for causing the processor set to perform computer operations further including:

causing a logical button to be displayed on a user interface corresponding to the given participant, the logical button being configured to initiate replaying the identified portions of the source audio signal in response to the logical button being activated,

wherein outputting statuses to the speaker includes:

dynamically combining the statuses, correlated with the amount of the source audio signal received by the respective participants, into a summary,

causing the summary to be displayed in real-time on a user interface corresponding to the speaker, and

dynamically updating the summary as the statuses change over time,

wherein the determining of the amount of the source audio signal received by a given participant includes:

producing first sentence segments by performing sentence segmentation on the source audio signal;

partitioning the first sentence segments based at least in part on respective types of statements made in the first sentence segments and/or respective subjects of the statements in the first sentence segments;

using the partitioned first sentence segments to generate a first sentence segmentation dataset for the source audio signal;

producing second sentence segments by performing sentence segmentation on the respective copy of the resulting audio signal received by the given participant, wherein the second sentence segments are not partitioned;

using the non-partitioned second sentence segments to generate a second sentence segmentation dataset for the respective copy of the resulting audio signal received by the given participant; and

comparing the first and second sentence segmentation datasets.