US 12,277,933 B2
Systems and methods for mobile speech therapy
Jared Duval, Santa Cruz, CA (US)
Assigned to THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, Oakland, CA (US)
Filed by The Regents of the University of California, Oakland, CA (US)
Filed on Jan. 24, 2022, as Appl. No. 17/648,798.
Claims priority of provisional application 63/141,329, filed on Jan. 25, 2021.
Prior Publication US 2022/0238110 A1, Jul. 28, 2022
Int. Cl. G10L 15/22 (2006.01); G06T 13/80 (2011.01); G10L 15/00 (2013.01); G10L 15/06 (2013.01)
CPC G10L 15/22 (2013.01) [G06T 13/80 (2013.01); G10L 15/005 (2013.01); G10L 15/063 (2013.01); G10L 2015/225 (2013.01)] 29 Claims
OG exemplary drawing
 
1. A computer-implemented method suitable for use with a portable electronic device, the method comprising:
receiving, via an audio input device of the portable electronic device, verbal speech input from a user and converting the received verbal speech input into an audio input signal;
applying, via a machine learning module of the portable electronic device, an acoustic model to the audio input signal;
performing, via an online processing module of the portable electronic device, at least one speech recognition operation on the audio input signal;
performing, via an offline processing module of the portable electronic device, at least one speech recognition operation on the audio input signal;
training the machine learning module using verbal samples, wherein each verbal sample is in one of a plurality of a spoken languages, and wherein the training is concurrent with the performing of the speech recognition operations by the online and offline processing modules;
generating, via an interactive game module of the portable electronic device, user feedback based on results from the at least one speech recognition operation performed by the online processing module and the at least one speech recognition operation by the offline processing module; and
providing, via a user interface of the portable electronic device, the user feedback to the user.