Automatic gain control for speech recognition
AssigneeIntel Corporation
InventorsPrzemyslaw Maziewski, Adam Kupryjanow
Life of this patent
Estimating the term…
Abstract
System and techniques for automatic gain control for speech recognition are described herein. An audio signal may be obtained. A signal-to-noise ratio (SNR) may be derived from the audio signal. The SNR may be compared to a threshold. A stored gain value may be updated when the SNR is beyond the threshold and the stored gain value may be applied to a descendant (e.g., later) of the audio signal otherwise.
Claims24
A system for automatic gain control for speech recognition, the system comprising:
- a sampler to obtain an audio signal;
- a signal processor to derive a signal-to-noise ratio (SNR) from the audio signal;
- a comparator to compare the SNR to a threshold, and
- a controller to:
- update a stored gain value when the SNR is beyond the threshold;
- and
- apply the stored gain value to a descendant of the audio signal when the SNR is not beyond the threshold.
At least one machine readable medium including instructions for automatic gain control for speech recognition, the instructions, when executed by a machine, cause the machine to perform operations comprising:
- obtaining an audio signal;
- deriving a signal-to-noise ratio (SNR) from the audio signal,
- comparing the SNR to a threshold;
- and
- updating a stored gain value when the SNR is beyond the threshold and applying the stored gain value to a descendant of the audio signal otherwise.
A method for automatic gain control for speech recognition, the method comprising:
- obtaining an audio signal;
- deriving a signal-to-noise ratio (SNR) from the audio signal;
- comparing the SNR to a threshold;
- and
- updating a stored gain value when the SNR is beyond the threshold and applying the stored gain value to a descendant of the audio signal otherwise.
Dependencies are inferred from the claim text.