Search for: All records

In one aspect, the disclosure relates to a smart pseudo-palate for use in a Smart Electropalatograph (EPG) for Linguistic and Medical Applications (SELMA) system. In one aspect, the pseudo-palate is constructed from a thin, flexible polymer membrane and having an embedded electrode array. The pseudo-palate is configured to detect tongue contacts during speech while causing minimal disturbance or interference with speech motion. The disclosed pseudo-palate in the SELMA system is integrated with a microcontroller, wireless electronic module, and external readout app. The disclosure, in another aspect, relates to integration of the pseudo-palate with a smart sports/health mouth guard containing a series of sensors for monitoring head impacts, body temperature, and heart rate. The SELMA system is capable of automated detection of neurological conditions and brain injury including, but not limited to, concussion, and neurological movement disorders, using acoustic, articulatory, and other biosignals from the device using deep data analysis. 

A deep learning Phonet model was evaluated as a method to measure lenition. Unlike quantitative acoustic methods, recurrent networks were trained to recognize the posterior probabilities of sonorant and continuant phonological features in a corpus of Argentinian Spanish. When applied to intervocalic and post-nasal voiced and voiceless stops, the approach yielded lenition patterns similar to those previously reported. Further, additional patterns also emerged. The results suggest the validity of the approach as an alternative or addition to quantitative acoustic measures of lenition.