Undesirable noise detection and management

Patent metadata

Field	Value
Publication number	US-2020280812-A1
Application number	US-202016842966-A
Country	US
Kind code	A1
Filing date	Apr 8, 2020
Priority date	Feb 28, 2019
Publication date	Sep 3, 2020
Grant date	—

Abstract

A communications management system (CMS) and related method receive registration information related to a plurality of participant systems (PSs) that communicate audio information between themselves. The CMS transmits a unique signal to each of the plurality of PSs that causes each of the plurality of PSs to produce a unique audio signal and detects an undesirable sound (US) in a PS of the plurality of PSs responsive to the transmission of the unique signal. Then, responsive to the detection of the US, the CMS applies a remedial action to the PS to initiate a reduction in a likelihood that the PS will produce a future US. Finally, the CMS repeats the operations of transmitting, detecting, and applying according to a predefined testing criteria.

First claim

What is claimed is:

1 . A computer program product for a communications management system (CMS), the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive registration information related to a plurality of participant systems (PSs) that communicate audio information between themselves; transmit a unique signal to each of the plurality of PSs that causes each of the plurality of PSs to produce a unique audio signal; detect an undesirable sound (US) in a PS of the plurality of PSs responsive to the transmission of the unique signal; responsive to the detection of the US, apply a remedial action to the PS to initiate a reduction in a likelihood that the PS will produce a future US; repeat the transmitting, detecting, and applying according to a predefined testing criteria; and responsive to the processor of the CMS receiving a positive or negative response to the transmission of the unique signal that indicates, respectively, a presence or absence of the US for a PS associated with the unique signal, storing data related to the positive or negative response in the prediction database.

2 . The computer program product of claim 1 , wherein the detection of a US in a PS is performed by determining a statistical likelihood of the PS being a source of the US using a t-test when a population size of the plurality of PSs is thirty or less, and a Z-test when a population size of the plurality of PSs is greater than thirty.

3 . The computer program product of claim 1 , wherein the detection of a US in a PS is performed by considering outliers or anomalies related to the transmission of the unique signal using a test selected from the group consisting of Cochran's C test and Grubb's test.

4 . The computer program product of claim 1 , wherein the unique audio signal is selected from the group consisting of: (a) a microburst with a duration of less than or equal to approximately 100 ms, and (b) a frequency that is generally inaudible to the human ear.

5 . The computer program product of claim 1 , wherein the remedial action is a volume adjustment.

6 . The computer program product of claim 5 , wherein the volume adjustment is a PS volume adjustment.

7 . The computer program product of claim 5 , wherein the volume adjustment is a CMS adjustment.

8 . The computer program product of claim 5 , wherein the volume adjustment is an adjustment to a PS speaker.

9 . The computer program product of claim 5 , wherein the volume adjustment is an adjustment to a PS microphone.

10 . The computer program product of claim 1 , wherein the remedial action is a message indicating a US problem.

11 . The computer program product of claim 1 , wherein the US is an echo.

12 . The computer program product of claim 1 , wherein the application of a remedial action comprises:
an application of a first remedial action conditioned upon a first level of detection of the US; and an application of a second remedial action that differs from the first remedial action conditioned upon a second level of detection of the US.

13 . A computer program product for a communications management system (CMS), the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive registration information related to a participant system (PS) of a plurality of PSs that communicate audio information between themselves; predict, according to a predefined likelihood threshold resulting in a positive determination, that an undesirable sound (US) will be present during a conference that the PS is participating in based on the received registration information and a historical indication of potential problems in the prediction information associated with the PS; and responsive to a positive prediction that the US will be present during the conference, preemptively and prior to the presence of the US, apply a remedial action to the PS to initiate a reduction in a likelihood that the US will be present during the conference prior to an actual detection of the US.

14 . The computer program product of claim 13 , wherein the remedial action is applied prior to or at a start of participation of the PS in the conference.

15 . The computer program product of claim 13 , wherein the processor is further configured to:
transmit a unique signal to each of the plurality of PSs that causes each of the plurality of PSs to produce a unique audio signal; detect an undesirable sound (US) in a PS of the plurality of PSs responsive to the transmission of the unique signal; responsive to the detection of the US, apply a remedial action to the PS to initiate a reduction in a likelihood that the PS will produce a future US; repeat the transmitting, detecting, and applying according to a predefined testing criteria.

16 . The computer program product of claim 15 , further comprising, responsive to the processor of the CMS receiving a positive or negative response to the transmission of the unique signal that indicates, respectively, a presence or absence of the US for a PS associated with the unique signal, storing data related to the positive or negative response in the prediction database.

17 . The computer program product of claim 15 , wherein the prediction information comprises data related to positive and negative responses that indicate, respectively, a presence or absence of the US for a PS associated with the unique signal to prior transmissions of a unique signal in prior conferences with respect to factors selected from the group consisting of hardware, software, user identity, and location.

18 . A computer-implemented method for managing a communications management system (CMS), the method comprising, using a processor for:
receiving registration information related to a participant system (PS) of a plurality of PSs that communicate audio information between themselves; predicting, according to a predefined likelihood threshold resulting in a positive determination, that an undesirable sound (US) will be present during a conference that the PS is participating in based on the received registration information and a historical indication of potential problems in the prediction information associated with the PS; and responsive to a positive prediction that the US will be present during the conference, preemptively and prior to the presence of the US, applying a remedial action to the PS to initiate a reduction in a likelihood that the US will be present during the conference prior to an actual detection of the US.

19 . The method of claim 18 , wherein the remedial action is applied prior to or at a start of participation of the PS in the conference.

20 . The method of claim 18 , further comprising:
transmitting a unique signal to each of the plurality of PSs that causes each of the plurality of PSs to produce a unique audio signal; detecting an undesirable sound (US) in a PS of the plurality of PSs responsive to the transmission of the unique signal; responsive to the detection of the US, applying a remedial action to the PS to initiate a reduction in a likelihood that the PS will produce a future US; repeating the transmitting, detecting, and applying according to a predefined testing criteria.

Assignees

• IBM

Inventors

• Boss Gregory J
• Bender Michael
• Fox Jeremy R
• E K Keerthi

Classifications

• H04L65/1083

  In-session procedures · CPC title

• H04R29/001 Primary

  for loudspeakers (H04R29/007 takes precedence) · CPC title

• H04R29/004 Primary

  for microphones (H04R29/007 takes precedence) · CPC title

• H04L65/762

  at the source  (reformatting of additional data in video distribution servers H04N21/2355) · CPC title

• H04S2400/15

  Aspects of sound capture and related signal processing for recording or reproduction · CPC title