Back to results
US 9,437,200 B2Granted
Noise suppression
AssigneeSkype
InventorsKarsten Vandborg Sorensen, Jon Anders Bergenheim, Koen Bernard Vos
Life of this patent
Estimating the term…
Abstract
A method and computing system for suppressing noise in an audio signal, comprising: receiving the audio signal at signal processing means; determining that another signal is input to the signal processing means, the input signal resulting from an activity which generates noise in the audio signal; and selectively suppressing noise in the audio signal in dependence on the determination that the input signal is input to the signal processing means to thereby suppress the generated noise in the audio signal.
Claims20
A method comprising:
- identifying an input signal that results from an activity which generates noise in an audio signal;
- and
- suppressing the noise in the audio signal in response to said identifying, said suppressing including:
- determining an elapsed time since a most recent detected speech component of the audio signal during which no speech components are detected in the audio signal;
- and
- muting the audio signal for a muting time period in response to determining that the elapsed time exceeds a pre-specified speech time period, the pre-specified speech time period being greater than the muting time period and corresponding to a period of time that is to be measured while no speech components are detected in the audio signal, the muting time period having a predetermined duration that is characteristic of a duration of the noise generated by the activity.
3 more elements
A computing system comprising:
- a signal processor configured to perform operations including identifying an input signal that results from an activity which generates noise in an audio signal;
- and
- a noise suppressor configured to perform operations including suppressing the noise in the audio signal, said suppressing including:
- determining an elapsed time since a most recent detected speech component of the audio signal during which no speech components are detected in the audio signal;
- and
- muting the audio signal for a muting time period in response to determining that the elapsed time exceeds a pre-specified speech time period, the pre-specified speech time period being greater than the muting time period and corresponding to a period of time that is to be measured while no speech components are detected in the audio signal, the muting time period having a predetermined duration that is characteristic of a duration of the noise generated by the activity.
3 more elements
A computing system comprising:
- one or more processors;
- and
- a memory device storing software that is configured to be executed by the one or more processors to cause the computing system to perform operations including:
- identifying an input signal that results from an activity which generates noise in an audio signal;
- and
- suppressing the noise in the audio signal in response to said identifying, said suppressing including:
- determining an elapsed time since a most recent detected speech component of the audio signal during which no speech components are detected in the audio signal;
- and
- muting the audio signal for a muting time period in response to determining that the elapsed time exceeds a pre-specified speech time period, the pre-specified speech time period being greater than the muting time period and corresponding to a period of time that is to be measured while no speech components are detected in the audio signal, the muting time period having a predetermined duration that is characteristic of a duration of the noise generated by the activity.
6 more elements
Dependencies are inferred from the claim text.