System and method to capture image of pinna and characterize human auditory anatomy using image of pinna

One or more non-transitory machine readable media comprising program code stored in memory and executable by a processor, the program code to:

• capture an image of a reference pinna;
• based on the image of the reference pinna, determine a non-linear transfer function which characterizes how sound is transformed at the reference pinna, wherein determining the non-linear transfer function comprises determining a first indication of match between the image of the reference pinna and a first image of a first pinna;
• determining a second indication of match between the image of the reference pinna and a second image of a second pinna, wherein first image is associated with a first head related transfer function (HRTF), the second image is associated with a second HRTF, and the reference pinna, first pinna, and second pinna are associated with different individuals;
• weighting the first HRTF based on the first indication of match;
• weighting the second HRTF based on the second indication of match;
• and combining the weighted first HRTF and weighted second HRTF to determine the non-linear transfer function which characterizes how sound is transformed at the reference pinna;
• and
• output, by a transducer, a signal indicative of one or more audio cues to facilitate spatial localization of sound via the reference pinna, wherein the one or more audio cues is based on the non-linear transfer function.

A system comprising:

• an audio device;
• computer instructions stored in memory and executable by a processor to perform the functions of:
• capturing, by the audio device, an image of a reference pinna;
• based on the image of the reference pinna, determining a non-linear transfer function which characterizes how sound is transformed at the reference pinna, wherein determining the non-linear transfer function comprises determining a first indication of match between the image of the reference pinna and a first image of a first pinna;
• determining a second indication of match between the image of the reference pinna and a second image of a second pinna, wherein first image is associated with a first head related transfer function (HRTF), the second image is associated with a second HRTF, and the reference pinna, first pinna, and second pinna are associated with different individuals;
• weighting the first HRTF based on the first indication of match;
• weighting the second HRTF based on the second indication of match;
• and combining the weighted first HRTF and weighted second HRTF to determine the non-linear transfer function which characterizes how sound is transformed at the reference pinna;
• and
• outputting, by a transducer of the audio device, a signal indicative of one or more audio cues to facilitate spatial localization of sound via the reference pinna, wherein the one or more audio cues is based on the non-linear transfer function.

A method comprising:

• capturing an image of a reference pinna;
• based on the image of the reference pinna, determining a non-linear transfer function which characterizes how sound is transformed at the reference pinna, wherein determining the non-linear transfer function comprises inputting the image into a neural network model which outputs the non-linear transfer function;
• and
• outputting, by a transducer, a signal indicative of one or more audio cues to facilitate spatial localization of sound via the reference pinna, wherein the one or more audio cues is based on the non-linear transfer function.