Methods and apparatus for targeted sound detection and characterization

A targeted sound detection apparatus a microphone array having two or more microphones M0 . . . MM;

• a plurality of filters coupled to each microphone, the filters being configured to filter input signals corresponding to sounds detected by the microphones and generate a filtered output;
• a processor coupled to the microphone array and the plurality of filters;
• a memory coupled to the processor;
• one or more sets of the filter parameters embodied in the memory, corresponding to one or more pre-calibrated listening zones, wherein each set of filter parameters is selected to detect portions of the input signals corresponding to sounds originating within a given listening zone and filters out sounds originating outside the given listening zone;
• the memory containing a set of processor executable instructions that, when executed,
• cause the apparatus to select a particular pre-calibrated listening zone at a runtime by applying to the plurality of filters a set of filter parameters corresponding to the particular pre-calibrated listening zone,
• whereby the apparatus may detect sounds originating within the particular pre-calibrated listening zone and filter out sounds originating outside the particular pre-calibrated listening zone;
• wherein the one or more pre-calibrated listening zones include a plurality of different listening zones, wherein the set of processor executable instructions includes one or more instructions which, when executed, cause the apparatus to:
• detect a sound with the microphone array;
• identify a particular listening zone containing a source of the sound;
• characterize the sound or the source of the sound;
• and
• emphasize or filter out the sound depending on how the sound is characterized.

A computer-readable medium having embodied therein computer executable instructions for performing a method for targeted sound detection using a microphone array having two or more microphones M0 . . . MM, each microphone being coupled to a plurality of filters, the filters being configured to filter input signals corresponding to sounds detected by the microphones thereby generating a filtered output, the method comprising:

• pre-calibrating a one or more sets of filter parameters for the plurality of filters to determine one or more corresponding pre-calibrated listening zones, wherein each set of filter parameters is selected to detect portions of the input signals corresponding to sounds originating within a given listening zone and filter out sounds originating outside the given listening sector;
• and
• selecting a particular pre-calibrated listening zone at a runtime by applying to the plurality of filters a set of filter coefficients corresponding to the particular pre-calibrated listening zone,
• whereby the microphone array may detect sounds originating within the particular listening zone and filters out sounds originating outside the particular listening zone;
• wherein the one or more pre-calibrated listening zones include a plurality of different listening zones, wherein the set of processor executable instructions includes one or more instructions which, when executed, cause the apparatus to:
• detect a sound with the microphone array;
• identify a particular listening zone containing a source of the sound;
• characterize the sound or the source of the sound;
• and
• emphasize or filter out the sound depending on how the sound is characterized.