US 12,136,416 B1
Private language model adaptation for speech recognition
Zhe Liu, Sunnyvale, CA (US); Ke Li, Baltimore, MD (US); and Fuchun Peng, Palo Alto, CA (US)
Assigned to Meta Platforms, Inc., Menlo Park, CA (US)
Filed by Meta Platforms, Inc., Menlo Park, CA (US)
Filed on Jul. 5, 2022, as Appl. No. 17/857,384.
Claims priority of provisional application 63/249,159, filed on Sep. 28, 2021.
Int. Cl. G10L 15/16 (2006.01); G10L 15/06 (2013.01); G10L 15/30 (2013.01); G10L 15/32 (2013.01)
CPC G10L 15/16 (2013.01) [G10L 15/063 (2013.01); G10L 15/30 (2013.01); G10L 15/32 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising, by a first computing device:
accessing a decoded hypothesis corresponding to an utterance;
computing a predicted probability of observing tokens in the decoded hypothesis by having a local first machine-learning model process the decoded hypothesis;
computing, for the tokens in the decoded hypothesis, confidence scores by having a second machine-learning model process the decoded hypothesis, wherein the confidence scores indicate a degree of confidence for the tokens to be observed at their position;
calculating a loss for the computed predicted probabilities of observing tokens in the decoded hypothesis based on the computed confidence scores; and
updating parameters of the local first machine-learning model based on the calculated loss.