US 12,387,619 B2
Systems and methods for grapheme-phoneme correspondence learning
Tom Dillon, Washington, DC (US)
Assigned to 617 EDUCATION INC., Washington, DC (US)
Filed by 617 Education Inc., Washington, DC (US)
Filed on May 2, 2024, as Appl. No. 18/653,629.
Application 18/653,629 is a continuation of application No. 18/152,625, filed on Jan. 10, 2023, granted, now 12,008,921.
Claims priority of provisional application 63/363,406, filed on Apr. 22, 2022.
Prior Publication US 2024/0282213 A1, Aug. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G09B 7/04 (2006.01); G06F 3/16 (2006.01); G09B 19/04 (2006.01); G10L 15/02 (2006.01); G10L 15/06 (2013.01); G10L 15/22 (2006.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01)
CPC G09B 7/04 (2013.01) [G06F 3/167 (2013.01); G09B 19/04 (2013.01); G10L 15/02 (2013.01); G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01); G10L 2015/025 (2013.01); G10L 2015/225 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for teaching grapheme-phoneme correspondence comprising:
a data augmentor implemented on at least one processor and configured to augment the spectrogram data for one or more sounds corresponding to one or more phonemes to provide augmented spectrogram data; and
a trainer implemented on at least one processor and configured to train a grapheme-phoneme model for grapheme-phoneme correspondence learning based on the augmented spectrogram data so that the grapheme-phoneme model determines whether a sound made by a human is representative of a phoneme for a grapheme.