Abstract: The various implementations described herein include techniques and apparatuses for handwriting and other user gesture detection and recognition. In one aspect, a method includes receiving, via one or more sensors of a wearable device worn by a user, neuromuscular data generated from performance of a hand gesture by the user. The method also includes generating, using one or more encoders, one or more encodings by encoding the neuromuscular data; and identifying, using a language model, one or more terms from the one or more encodings. The method further includes causing display of the one or more terms to the user during performance of the hand gesture.

Abstract: The various implementations described herein include methods and systems for power-efficient processing of neuromuscular signals. In one aspect, a method includes: (i) obtaining a first set of neuromuscular signals; (ii) after determining, using a low-power detector, that the first set of neuromuscular signals require further processing to confirm that a predetermined in-air hand gesture has been performed: (a) processing the first set of neuromuscular signals using a high-power detector; and (b) in accordance with a determination that the processing indicates that the predetermined in-air hand gesture did occur, registering an occurrence of the predetermined in-air hand gesture; (iii) receiving a second set of neuromuscular signals; and (iv) after determining, using the low-power detector and not using the high-power detector, that a different predetermined in-air hand gesture was performed, performing an action in response to the different predetermined in-air hand gesture.