Occupancy tracking using sound recognition

An occupancy tracking method, comprising:

• receiving a plurality of sound samples over a predetermine time period;
• computing an audio signature for each sound sample from the plurality of sound samples, wherein the audio signature comprises a numerical value that uniquely identifies characteristics of an audio signal;
• determining a direction of arrival for each sound sample from the plurality of sound samples, wherein the direction of arrival identifies a direction for a source for the sound sample;
• populating entries in a voice data log for the plurality of sound samples, wherein each entry comprises:
• a timestamp that identifies when a sound sample was recorded;
• an audio signature that describes characteristics of the sound sample;
• and
• a direction of arrival for the sound sample;
• identifying one or more clusters for the populated entries based on an audio signature that is associated with the populated entries, wherein each cluster comprises audio signatures that are associated with a voice of a person;
• determining a number of clusters that are identified;
• determining a predicted occupancy level based on the number of clusters that are identified, wherein the predicted occupancy level is equal to the number of clusters that are identified;
• and
• controlling a Heating, Ventilation, and Air Conditioning (HVAC) system based on the predicted occupancy level, wherein the HVAC system is configured to control a temperature of a space.

An occupancy tracking system, comprising:

• a Heating, Ventilation, and Air Conditioning (HVAC) system, wherein the HVAC system is configured to control a temperature of a space;
• and
• a thermostat in signal communication with the HVAC system, configured to:
• receive a plurality of sound samples over a predetermine time period;
• compute an audio signature for each sound sample from the plurality of sound samples, wherein the audio signature comprises a numerical value that uniquely identifies characteristics of an audio signal;
• determine a direction of arrival for each sound sample from the plurality of sound samples, wherein the direction of arrival identifies a direction for a source for the sound sample;
• populate entries in a voice data log for the plurality of sound samples, wherein each entry comprises:
• a timestamp that identifies when a sound sample was recorded;
• an audio signature that describes characteristics of the sound sample;
• and
• a direction of arrival for the sound sample;
• identify one or more clusters for the populated entries based on an audio signature that is associated with the populated entries, wherein each cluster comprises audio signatures that are associated with a voice of a person;
• determine a number of clusters that are identified;
• determine a predicted occupancy level based on the number of clusters that are identified, wherein the predicted occupancy level is equal to the number of clusters that are identified;
• and
• control the HVAC system based on the predicted occupancy level.