Contextual beamforming to improve signal-to-noise ratio sensitive audio input processing efficiency in noisy environments

1. An audio processing system, comprising:

a microphone array including at least two microphones and configured to provide an audio signal from an environment surrounding the microphone array; and

a speech detection system configured to receive the audio signal, and to process the audio signal to a) characterize a first voice of a first user and a second voice of a second user, b) detect that the first user is speaking utilizing a speaker diarization model to distinguish the first voice from the second voice, c) determine a first direction relative to the audio array when the first user is located at a first location within the environment, d) provide beamforming processing on the audio signal in the first direction, and e) provide a processed audio signal based upon the beamforming processing

wherein the audio processing system is configured to reduce noise in the processed audio signal.

2. The audio processing system of claim 1 , wherein the speech detection system is further configured to determine that the first user has moved form the first location within the environment to a second location within the environment.

3. The audio processing system of claim 2 , wherein the speech detection system is further configured to determine a second direction relative to the audio array when the first user is located at the second location.

4. The audio processing system of claim 3 , wherein the speech detection system is further configured to provide beamforming processing on the audio signal in the second direction.

5. The audio processing system of claim 1 , wherein the speech detection system is further configured to process the audio signal to a) detect that the second user is speaking, b) determine a third direction relative to the audio array when the second user is located at a third location within the environment, and c) provide beamforming processing on the audio signal in the third direction.

6. The audio processing system of claim 1 , wherein, in determining the first direction, the speech detection system is further configured to determine a time delay in the audio signal between the microphones of the microphone array.

7. The information handling system of claim 1 , wherein, in detecting that the first user is speaking, the speech detection system utilizes a voice identification algorithm including at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm.

8. A method comprising:

providing, by a microphone array of an audio processing system, an audio signal from an environment surrounding the microphone array, wherein the microphone array includes at least two microphones;

characterizing a first voice of a first user and a second voice of a second user;

processing the audio signal to a) detect that the first user is speaking utilizing a speaker diarization model to distinguish the first voice from the second voice, b) determine a first direction relative to the audio array when the first user is located at a first location within the environment, and c) provide beamforming processing on the audio signal in the first direction;

providing a processed audio signal based upon the beamforming processing; and

reducing noise in the processed audio signal.

9. The method of claim 8 , further comprising determining that the first user has moved form the first location within the environment to a second location within the environment.

10. The method of claim 9 , further comprising determining a second direction relative to the audio array when the first user is located at the second location.

11. The method of claim 10 , further comprising providing beamforming processing on the audio signal in the second direction.

12. The method of claim 8 , wherein detecting that the first user is speaking is based upon the characterization of the first voice.

13. The method of claim 8 , further comprising processing the audio signal to a) detect that the second user is speaking, b) determine a third direction relative to the audio array when the second user is located at a third location within the environment, and c) provide beamforming processing on the audio signal in the third direction.

14. The method of claim 8 wherein, in detecting that the first user is speaking, the method further comprises utilizing at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm.

15. An information handling system, comprising:

a microphone array including at least two microphones and configured to provide an audio signal from an environment surrounding the microphone array; and

a processor configured to provide an audio processing system including:

a speech detection system configured to receive the audio signal, and to process the audio signal to a) characterize a first voice of a first user and a second voice of a second user, b) detect that the first user is speaking utilizing a speaker diarization model to distinguish the first voice from the second voice, c) determine a first direction relative to the audio array when the first user is located at a first location within the environment, d) provide beamforming processing on the audio signal in the first direction, and e) provide a processed audio signal based upon the beamforming processing; and

a neural network noise reduction module configured to reduce noise in the processed audio signal.

16. The information handling system of claim 15 , wherein, in detecting that the first user is speaking, the speech detection system utilizes a voice identification algorithm including at least one of a frequency estimation algorithm, a pattern matching algorithm, a neural network algorithm, a matrix representation algorithm, a vector quantization algorithm, and a decision tree algorithm.