Lightweight full 360 audio source location detection with two microphones

A method, comprising:

• identifying a pre-determined acoustic barrier filter, wherein the pre-determined acoustic barrier filter coincides with a physical acoustic barrier;
• receiving an audio signal within a time window at a first microphone and a second microphone;
• calculating a first measure of variability of a direct difference of the audio signal received at the first microphone and the second microphone, a second measure of variability of a delayed difference of the audio signal received at the first microphone and the second microphone, a third measure of variability of a filtered direct difference of the audio signal received at the first microphone and the second microphone, wherein the audio signal is filtered by the pre-determined acoustic barrier filter, and a fourth measure of variability of a filtered delayed difference of the audio signal received at the first microphone and the second microphone, wherein the audio signal is filtered by the pre-determined acoustic barrier filter;
• concatenating the first measure of variability, the second measure of variability, the third measure of variability, and the fourth measure of variability to form a feature vector;
• and
• inputting the feature vector into a location classifier to obtain an audio source location.

At least one storage device or storage disk comprising instructions to cause a computing device to at least:

• identify a pre-determined acoustic barrier filter, wherein the pre-determined acoustic barrier filter coincides with a physical acoustic barrier;
• receive an audio signal within a time window at a first microphone and a second microphone;
• calculate a first measure of variability of a direct difference of the audio signal received at the first microphone and the second microphone, a second measure of variability of a delayed difference of the audio signal received at the first microphone and the second microphone, a third measure of variability of a filtered direct difference of the audio signal received at the first microphone and the second microphone, wherein the audio signal is filtered by the pre-determined acoustic barrier filter, and a fourth measure of variability of a filtered delayed difference of the audio signal received at the first microphone and the second microphone, wherein the audio signal is filtered by the pre-determined acoustic barrier filter;
• concatenate the first measure of variability, the second measure of variability, the third measure of variability, and the fourth measure of variability to form a feature vector;
• and
• input the feature vector into a location classifier to obtain an audio source location.