Abstract: Systems and methods of the present disclosure are directed to automatic control of mute controllers for participants in videoconferences. For example, a method for automatically controlling a mute control associated with a participant during a videoconference includes obtaining communication data associated with the participant participating in the videoconference. The communication data includes audio signals associated with the participant and/or visual signals associated with the participant. The method includes processing the communication data by a gate control model to generate an output. The output is indicative of an intent of the participant to communicate with other participants of the videoconference. The method includes generating a noise gate status based at least in part on the output associated with the gate control model. The method includes automatically controlling the mute control of the participant based at least in part on the noise gate status.

Abstract: A method for detecting and flagging problems in videoconferencing is provided. The method includes collecting, by a processing device of a user videoconferencing device, one or more sets of acoustic parameters associated with a conference room. Each set of the one or more sets of acoustic parameters is associated with a video conference attended by a corresponding plurality of users. The method further includes determining whether a first set of the one or more sets of acoustic parameters suggest an action to be performed to improve the first set of acoustic parameters associated with the video conference. The method further includes providing at least one of the one or more sets of acoustic parameters associated with the conference room or the action to be performed to improve the first set of acoustic parameters.

Abstract: A method for detecting and flagging problems in videoconferencing is provided. The method includes measuring, by a processing device of a user videoconferencing device, a first set of acoustic data associated with a conference room during a video conference attended by a plurality of users. The first set of acoustic data indicates one or more acoustic parameters, including the reverberation time, the signal-to-noise ratio, or the absolute noise level of the conference room. The method further includes comparing the one or more first acoustic parameters to one or more thresholds during the video conference. Moreover, the method includes providing at least one of the first acoustic parameters or a result of the comparison to the at least one user during the video conference.

Abstract: The present disclosure describes aspects of adaptive energy limiting for transient noise suppression. In some aspects, an adaptive energy limiter sets a limiter ceiling for an audio signal to full scale and receives a portion of the audio signal. For the portion of the audio signal, the adaptive energy limiter determines a maximum amplitude and evaluates the portion with a neural network to provide a voice likelihood estimate. Based on the maximum amplitude and the voice likelihood estimate, the adaptive energy limiter determines that the portion of the audio signal includes noise. In response to determining that the portion of the audio signal includes noise, the adaptive energy limiter decreases the limiter ceiling and provides the limiter ceiling to a limiter module effective to limit an amount of energy of the audio signal. This may be effective to prevent audio signals from carrying full energy transient noise into conference audio.

Abstract: The present disclosure describes aspects of adaptive energy limiting for transient noise suppression. In some aspects, an adaptive energy limiter sets a limiter ceiling for an audio signal to full scale and receives a portion of the audio signal. For the portion of the audio signal, the adaptive energy limiter determines a maximum amplitude and evaluates the portion with a neural network to provide a voice likelihood estimate. Based on the maximum amplitude and the voice likelihood estimate, the adaptive energy limiter determines that the portion of the audio signal includes noise. In response to determining that the portion of the audio signal includes noise, the adaptive energy limiter decreases the limiter ceiling and provides the limiter ceiling to a limiter module effective to limit an amount of energy of the audio signal. This may be effective to prevent audio signals from carrying full energy transient noise into conference audio.

Abstract: The present disclosure describes aspects of adaptive energy limiting for transient noise suppression. In some aspects, an adaptive energy limiter sets a limiter ceiling for an audio signal to full scale and receives a portion of the audio signal. For the portion of the audio signal, the adaptive energy limiter determines a maximum amplitude and evaluates the portion with a neural network to provide a voice likelihood estimate. Based on the maximum amplitude and the voice likelihood estimate, the adaptive energy limiter determines that the portion of the audio signal includes noise. In response to determining that the portion of the audio signal includes noise, the adaptive energy limiter decreases the limiter ceiling and provides the limiter ceiling to a limiter module effective to limit an amount of energy of the audio signal. This may be effective to prevent audio signals from carrying full energy transient noise into conference audio.

Abstract: A method for detecting and flagging problems in videoconferencing is provided. The method includes measuring, by a processing device of a user videoconferencing device, a first set of acoustic data associated with a conference room during a video conference attended by a plurality of users. The first set of acoustic data indicates one or more acoustic parameters, including the reverberation time, the signal-to-noise ratio, or the absolute noise level of the conference room. The method further includes comparing the one or more first acoustic parameters to one or more thresholds during the video conference. Moreover, the method includes providing at least one of the first acoustic parameters or a result of the comparison to the at least one user during the video conference.

Abstract: A method for detecting and flagging problems in videoconferencing is provided. The method includes measuring, by a processing device of a videoconferencing device, a first set of acoustic data associated with a conference room during a video conference attended by a plurality of users. The first set of acoustic data indicates one or more acoustic parameters, including the reverberation time, the signal-to-noise ratio, or the absolute noise level of the conference room. The method further includes determining whether the acoustic parameters suggest that a feedback is to be provided to one or more of the users regarding an action to be performed to improve the acoustic parameters during the video conference. Moreover, the method includes responsive to determining that the feedback is to be provided to at least one user, providing the feedback to the at least one user during the video conference.

Abstract: A method for detecting and flagging problems in videoconferencing is provided. The method includes measuring, by a processing device of a videoconferencing device, a first set of acoustic data associated with a conference room during a video conference attended by a plurality of users. The first set of acoustic data indicates one or more acoustic parameters, including the reverberation time, the signal-to-noise ratio, or the absolute noise level of the conference room. The method further includes determining whether the acoustic parameters suggest that a feedback is to be provided to one or more of the users regarding an action to be performed to improve the acoustic parameters during the video conference. Moreover, the method includes responsive to determining that the feedback is to be provided to at least one user, providing the feedback to the at least one user during the video conference.

Abstract: The present disclosure describes aspects of adaptive energy limiting for transient noise suppression. In some aspects, an adaptive energy limiter sets a limiter ceiling for an audio signal to full scale and receives a portion of the audio signal. For the portion of the audio signal, the adaptive energy limiter determines a maximum amplitude and evaluates the portion with a neural network to provide a voice likelihood estimate. Based on the maximum amplitude and the voice likelihood estimate, the adaptive energy limiter determines that the portion of the audio signal includes noise. In response to determining that the portion of the audio signal includes noise, the adaptive energy limiter decreases the limiter ceiling and provides the limiter ceiling to a limiter module effective to limit an amount of energy of the audio signal. This may be effective to prevent audio signals from carrying full energy transient noise into conference audio.