Techniques for monitoring and detecting respiration

A device for monitoring respiration, the device comprising:

• one or more input interfaces;
• a processor coupled to the input interfaces and adapted to execute one or more processes;
• and
• a memory operable to store instructions executable by the processor, wherein the instructions, when executed by the processor, are operable to:
• receive audio data representing sound detected by an input interface on a device;
• determine a frequency spectrum of amplitude distributions for one or more frequencies represented by the audio data;
• identify a first frequency band including a first set of frequencies associated with respiration, a second frequency band including a second set of frequencies associated with noise, and a third frequency band including a third set of frequencies associated with voice harmonics;
• apply a gain to the first set of frequencies to create an amplified first frequency band;
• apply a filter to the second set of frequencies to create a nulled second frequency band;
• invert the third set of frequencies of the third frequency band to create an inverted third frequency band;
• determine the frequency spectrum corresponds to an exhalation based on a slope value between amplitude distributions of the amplified first frequency band and at least a portion of amplitude distributions of the inverted third frequency band;
• and
• modify an experience presented to a user of the device based on the exhalation.

A tangible, non-transitory, computer-readable media having instructions encoded thereon, the instructions, when executed by a processor, are operable to:

• receive audio data representing sound detected by an input interface on a device;
• determine a frequency spectrum of amplitude distributions for one or more frequencies represented by the audio data;
• identify a first frequency band including a first set of frequencies associated with respiration, a second frequency band including a second set of frequencies associated with noise, and a third frequency band including a third set of frequencies associated with voice harmonics;
• apply a gain to the first set of frequencies to create an amplified first frequency band;
• apply a filter to the second set of frequencies to create a nulled second frequency band;
• invert the third set of frequencies of the third frequency band to create an inverted third frequency band;
• determine the frequency spectrum corresponds to an exhalation based on a slope value between amplitude distributions of the amplified first frequency band and at least a portion of amplitude distributions of the inverted third frequency band;
• and
• modify an experience presented to a user of the device based on the exhalation.