Multi-mode noise cancellation for voice detection

At least one non-transitory computer storage media, having instructions stored thereon that, when executed by at least one processor of a computing system, cause the computing system to:

• initialize a speech microphone of a voice-detecting headset, the voice-detecting headset also having a plurality of noise-detecting microphones;
• detect an ambient noise in a speech signal received by the speech microphone;
• dynamically select a noise-cancelling algorithm from a plurality of different noise-cancelling algorithms based at least on a sensed energy level of the detected ambient noise, wherein the selected noise-cancelling algorithm comprises:
• a first noise-cancelling algorithm useable for reducing a first type of ambient noise signal present in the speech signal, the first noise-cancelling algorithm selected based on the sensed energy level being below a threshold, or
• a second noise-cancelling algorithm useable for reducing a second type of ambient noise signal present in the speech signal, wherein the second noise-cancelling algorithm is selected based on the sensed energy level being above the threshold;
• optimize the speech signal received by the speech microphone by cancelling an ambient noise signal from the speech signal using the dynamically selected noise-cancelling algorithm, the ambient noise signal being received by the speech microphone and at least one dynamically selected noise-detecting microphone of the plurality of noise-detecting microphones;
• and
• communicate the optimized speech signal to the voice-detecting headset for interpretation.

A computerized system comprising:

• at least one processor;
• and
• at least one computer storage media storing computer-useable instructions thereon that, when executed by the at least one processor, causes the at least one processor to:
• detect an ambient noise in a speech signal received by a voice-detecting headset comprising a speech microphone and a plurality of noise-detecting microphones;
• dynamically select a noise-cancelling algorithm from a plurality of different noise-cancelling algorithms based on a detected ambient noise level, wherein the dynamically selected noise-cancelling algorithm comprises:
• a first noise-cancelling algorithm useable for reducing a first type of ambient noise signal present in the speech signal, the first noise-cancelling algorithm selected based on the detected ambient noise level being below a threshold, or
• a second noise-cancelling algorithm useable for reducing a second type of ambient noise signal present in the speech signal, the second noise-cancelling algorithm selected based on the detected ambient noise level being above the threshold;
• determine that one or more of the plurality of noise-detecting microphones is detecting higher energy levels of the ambient noise compared to energy levels of the ambient noise detected by the remaining noise-detecting microphones;
• and
• optimize the speech signal received by the speech microphone by cancelling an ambient noise signal from the speech signal using the dynamically selected noise-cancelling algorithm, the ambient noise signal received at least by the speech microphone and the one or more of the plurality of noise-detecting microphones.