Proactive audio optimization for conferences
AssigneeCisco Technology, Inc.
InventorsDerek Engi, Gonzalo Salgueiro
Life of this patent
Estimating the term…
Abstract
In one embodiment, a device obtains audio data from one or more past conferences. A prediction model that predicts when participants of a conference will speak is generated based on the audio data from the one or more past conferences. The device uses the prediction model to predict a speech distribution for participants of a particular conference. Then, the device proactively optimizes audio parameters of the particular conference based on its predicted speech distribution.
Claims18
A method comprising:
- obtaining, by a device, audio data from one or more past conferences;
- generating, by the device, a prediction model that predicts when participants of a conference will speak based on the audio data from the one or more past conferences;
- predicting, by the device and using the prediction model, a speech distribution for participants of a particular conference, wherein the speech distribution indicates when and how long each participant will speak during the particular conference;
- and
- proactively optimizing, by the device, audio parameters of the particular conference based on its predicted speech distribution to prioritize audio output by a particular participant during the particular conference, wherein the particular participant is predicted to be a primary speaker during the particular conference.
An apparatus, comprising:
- a network interface to communicate with a computer network;
- a processor coupled to the network interface and configured to execute one or more processes;
- and
- a memory configured to store a process that is executed by the processor, the process when executed configured to:
- obtain audio data from one or more past conferences;
- generate a prediction model that predicts when participants of a conference will speak based on the audio data from the one or more past conferences;
- predict, using the prediction model, a speech distribution for participants of a particular conference, wherein the speech distribution indicates when and how long each participant will speak during the particular conference;
- and
- proactively optimize audio parameters of the particular conference based on its predicted speech distribution to prioritize audio output by a particular participant during the particular conference, wherein the particular participant is predicted to be a primary speaker during the particular conference.
A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
- obtaining, by the device, audio data from one or more past conferences;
- generating, by the device, a prediction model that predicts when participants of a conference will speak based on the audio data from the one or more past conferences;
- predicting, by the device and using the prediction model, a speech distribution for participants of a particular conference, wherein the speech distribution indicates when and how long each participant will speak during the particular conference;
- and
- proactively optimizing, by the device, audio parameters of the particular conference based on its predicted speech distribution to prioritize audio output by a particular participant during the particular conference, wherein the particular participant is predicted to be a primary speaker during the particular conference.
Dependencies are inferred from the claim text.