US 11,887,602 B1
Audio-based device locationing
Brendon Jude Wilson, San Jose, CA (US); Henry Michael D Souza, San Diego, CA (US); Cindy Angie Hou, Mountain View, CA (US); Christopher Evans, Somerville, MA (US); Sumit Garg, Acton, MA (US); and Ravina Chopra, Austin, TX (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Dec. 10, 2021, as Appl. No. 17/547,894.
Int. Cl. G10L 15/30 (2013.01); G10L 19/02 (2013.01); G10L 15/22 (2006.01); G06F 3/16 (2006.01); G10L 19/018 (2013.01)
CPC G10L 15/30 (2013.01) [G06F 3/165 (2013.01); G06F 3/167 (2013.01); G10L 15/22 (2013.01); G10L 19/018 (2013.01); G10L 19/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing system comprising:
a first device configured to output audio corresponding to an acoustic fingerprint, the audio including a watermark corresponding to an encoded representation of a device identifier of the first device;
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the computing system to:
receive, by a second device, the audio;
determine the audio corresponds to the acoustic fingerprint;
determine, using a decoder and based at least in part on determining the audio corresponds to the acoustic fingerprint, the device identifier encoded in the audio;
generate first data representing a first spectral energy of the audio as received by the second device;
determine, using the first spectral energy, second data representing an attenuation experienced by the audio as the audio traveled from the first device to the second device;
determine a first matrix representing a first spatial position of the first device relative to the second device; and
generate, based on the second data, a second matrix representing a second spatial position of the first device relative to the second device.