Automatic correction of erroneous audio setting

Patent metadata

Field	Value
Publication number	US-11502863-B2
Application number	US-202016877059-A
Country	US
Kind code	B2
Filing date	May 18, 2020
Priority date	May 18, 2020
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

Electronic conferences can often be the source of frustration and wasted resources as participants may be forced to contend with extraneous sounds, such as conversations not intended for the conference, provided by an endpoint that should be muted. Similarly, participants may speak with the intention of providing their speech to the conference but speak while their associated endpoint is muted. As a result, the conference may be awkward and lack a productive flow while erroneously muted or non-muted endpoints are addressed. By detecting erroneous audio settings, endpoints can be prompted or automatically corrected to have the appropriate audio state.

First claim

What is claimed is:

1. A conference server, comprising:
a network interface to a network;
a storage component comprising a non-transitory storage device;
a processor, comprising at least one microprocessor; and
wherein the processor, upon accessing machine-executable instructions, cause the processor to perform:
broadcasting conference content, via the network, to each of a plurality of endpoints and wherein the conference content comprises an audio portion received from a contributing endpoint of the plurality of endpoints;
accessing audio profiles of a number of participants, each of the number of participants utilizing one of the plurality of endpoints, wherein each of the audio profiles characterizes speech;
identifying a participant audio profile, from the audio profiles, that corresponds to a participant of the number of participants, upon detecting that the conference content comprises a spoken name and, following the spoken name, hearing conference content comprising speech from the participant;
determining whether the audio portion comprises human speech that is extraneous to the conference content comprising further determining whether the conference content comprises speech from the participant that matches the participant audio profile associated with extraneous speech; and
upon determining that the audio portion comprises human speech that is extraneous to the conference content, executing a muting action to exclude the audio portion from the conference content.

2. The conference server of claim 1 , wherein the processor performs executing the muting action, further comprising, signaling the contributing endpoint to cause the contributing endpoint to energize a muting prompt circuit.

3. The conference server of claim 1 , wherein:
the participant audio profile of the participant comprises at least one of speaking volume, pitch, range, tone, or pace of speaking; and
wherein determining whether the audio portion is extraneous to the conference content, further comprises, determining that at least one of speaking volume, pitch, range, tone, or pace of speaking of the audio portion differs from the at least one of speaking volume, pitch, range, tone, or pace of speaking of the participant audio profile.

4. The conference server of claim 3 , wherein the processor determines that the audio portion comprises human speech that is extraneous to the conference content upon determining that the at least one of speaking volume, pitch, range, tone, or pace of speaking of the audio portion differs from the at least one of speaking volume, pitch, range, tone, or pace of speaking of the audio profile and that the difference is greater than a previously determined threshold.

5. The conference server of claim 1 , wherein the participant audio profile comprises at least one of speaking volume, pitch, range, tone, or pace of speaking as sampled from the conference content that follows the participant being addressed by name by another participant associated with a different one of the plurality of endpoints.

6. The conference server of claim 1 , wherein the participant audio profile of the participant characterizes speech provided by the participant with regard to a sound attribute comprising a first spoken language; and
wherein determining whether the audio portion comprises human speech that is extraneous to the conference content, further comprises, determining if the audio portion comprises a second spoken language.

7. The conference server of claim 1 , wherein the processor further performs, causing each of the plurality of endpoints to present indicia of the muting action associated with the contributing endpoint.

8. A conference server, comprising:
a network interface to a network;
a storage component comprising a non-transitory storage device;
a processor, comprising at least one microprocessor; and
wherein the processor, upon accessing machine-executable instructions, cause the processor to perform:
broadcasting conference content, via the network, to each of a plurality of endpoints and wherein the conference content selectively comprises an audio portion received from a contributing endpoint of the plurality of endpoints;
accessing an audio profile of a number of participants each utilizing one of the plurality of endpoints, wherein each of the audio profiles characterizes speech;
identifying an audio profile of a participant, from the audio profiles, that corresponds to the participant upon detecting the conference content comprises a spoken name and, following the spoken name, hearing conference content comprising speech from the participant;
determining whether the audio portion is muted, wherein the processor receives the audio portion from the contributing endpoint and omits the audio portion from the conference content comprising further determining whether the conference content comprises speech from the participant that matches the participant's audio profile associated with extraneous speech;
upon determining that the audio portion is muted, determining whether the contributing endpoint is erroneously muted and wherein the audio portion comprises encoded sound and wherein the processor determines that the contributing endpoint is erroneously muted further comprising, determining that the encoded sound comprises human speech from the participant that matches the participant's audio profile associated with non-extraneous speech; and
when erroneously muted, executing an unmuting action to include the audio portion in the conference content.

9. The conference server of claim 8 , wherein the processor performs executing the unmuting action, further comprising, signaling the contributing endpoint to cause the contributing endpoint to energize an unmuting prompt circuit.

10. The conference server of claim 8 , wherein the processor performs the determination that the contributing endpoint is erroneously muted, further comprising:
upon determining the encoded sound comprises speech, accessing the audio profile of the participant, wherein in the audio profile characterizes speech provided by the participant while contributing speech to the conference content;
determining whether the audio portion comprises human speech that is extraneous to the conference content, further comprising, determining whether at least one of speaking volume, pitch, range, tone, or pace of speaking of the audio portion differs from the at least one of speaking volume, pitch, range, tone, or pace of speaking of the audio profile; and
when the audio portion comprises human speech that is determined not to be extraneous, performing the unmuting action.

11. The conference server of claim 8 , wherein the processor performs the determination that the contributing endpoint is erroneously muted, further comprising, upon determining the encoded sound comprises speech that follows the participant being addressed by name by another participant associated with a different one of the plurality of endpoints.

12. A method for correcting an erroneous audio setting, comprising:
broadcasting conference content, via a network, to each of a plurality of endpoints, wherein the conference content comprises audio content provided by one or more of the plurality of endpoints;
accessing audio profiles of a number of participants each utilizing one of the plurality of endpoints, wherein each of the audio profiles characterizes speech;
identifying an audio profile of a participant, from a plurality of audio profiles, that corresponds to the participant upon detecting that the conference content comprises a spoken name and, following the spoken name, hearing conference content comprising speech fro

Assignees

• Avaya Man Lp

Inventors

• Deole Pushkar Yashavant
• Chopdekar Sandesh
• Daga Navin

Classifications

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• H04M3/567

  Multimedia conference systems · CPC title

• H04M3/566

  relating to a participants right to speak (arrangements for multi-party communication with floor control, e.g. for conferences, H04L65/4038, H04L65/4046, H04L65/4053) · CPC title

• H04M3/568 Primary

  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 title

• H04L12/1822 Primary

  Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission · CPC title