US 12,482,461 B2
Systems, methods, and devices for wakeup word detection with continuous learning
Ashutosh Pandey, Irvine, CA (US); Daniel Watson, Austin, TX (US); and Aidan Smyth, Milpitas, CA (US)
Assigned to CYPRESS SEMICONDUCTOR CORPORATION, San Jose, CA (US)
Filed by Cypress Semiconductor Corporation, San Jose, CA (US)
Filed on Aug. 18, 2022, as Appl. No. 17/820,820.
Prior Publication US 2024/0062755 A1, Feb. 22, 2024
Int. Cl. G10L 15/22 (2006.01); G06F 1/3206 (2019.01); G10L 15/02 (2006.01); G10L 15/08 (2006.01)
CPC G10L 15/22 (2013.01) [G06F 1/3206 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving an audio input at an audio front end circuit;
identifying, using a first circuit, a wake word based, at least in part, on the received audio input;
mapping, using a language processing model, a distribution of decisions made by a second circuit in a latent space of the second circuit to a latent space of the first circuit being a low-dimensional space, and the audio input comprising audio data in an observable space;
generating a designated threshold of accuracy based on a distance threshold between a positive distribution of decisions and a negative distribution of decisions made by the first circuit in the latent space of the first circuit and representing correct and incorrect decisions made by the first circuit as determined relative to the distribution of decisions made by the second circuit after being mapped to the low-dimensional latent space of the first circuit;
determining if the identifying performed by the first circuit should be adjusted based, at least in part, on the designated threshold of accuracy, and
adjusting, using one or more processors, wake word detection operations of the first circuit responsive to determining that the distance between the distributions is greater than the designated threshold of accuracy.