US 11,741,971 B1
Accessing and encoding data using a least significant bit encoding algorithm
Longhua You, Seattle, WA (US); Yingwei Li, Bellevue, WA (US); Yan Cui, Seattle, WA (US); Mayank Thakore, Seattle, WA (US); Tianbin Jiang, Bothell, WA (US); Chunzhang Mo, Seattle, WA (US); Wei Huang, Seattle, WA (US); Shuo Li, Seattle, WA (US); and Ross William Snider, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 30, 2021, as Appl. No. 17/363,718.
Int. Cl. G06F 16/33 (2019.01); G06F 40/263 (2020.01); G06F 9/451 (2018.01); G10L 19/00 (2013.01); H04L 49/40 (2022.01); G06F 21/10 (2013.01); G10L 15/08 (2006.01)
CPC G10L 19/00 (2013.01) [G10L 15/08 (2013.01); G10L 2015/088 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a first device, a first request for access to audio data;
determining, using first policy data, that the first device is authorized to access the audio data;
determining that the audio data represents speech captured by a user device;
in response to the audio data representing speech, determining, using second policy data, that the audio data is to be encoded according to a first encoding scheme, the first encoding scheme using a least significant bit algorithm;
receiving the audio data from data storage;
based at least in part on the first encoding scheme and the first device, determining first encoding data representing a device identifier of the first device;
using the first encoding scheme to determine a first portion of the audio data to be overwritten to allow insertion of the first encoding data;
using the audio data to determine first encoded audio data representing the speech, the first encoded audio data including the first encoding data instead of the first portion of the audio data; and
sending, to the first device, the first encoded audio data.