10.23641/asha.8636948.v1 Gabriel J. Cler Gabriel J. Cler Katharine R. Kolin Katharine R. Kolin Jacob P. Noordzij Jr. Jacob P. Noordzij Jr. Jennifer M. Vojtech Jennifer M. Vojtech Susan K. Fager Susan K. Fager Cara E. Stepp Cara E. Stepp Optimized and predictive phonemic interfaces (Cler et al., 2019) ASHA journals 2019 speech optimized predictive interface computational communication augmentative and alternative communication motor speech disorder impairment severe phoneme layout targets controls static prediction training methods clinical clinician Linguistic Processes (incl. Speech Production and Comprehension) Communication Technology and Digital Media Studies 2019-07-15 21:27:51 Journal contribution https://asha.figshare.com/articles/journal_contribution/Optimized_and_predictive_phonemic_interfaces_Cler_et_al_2019_/8636948 <div><b>Purpose: </b>We empirically assessed the results of computational optimization and prediction in communication interfaces that were designed to allow individuals with severe motor speech disorders to select phonemes and generate speech output.</div><div><b>Method: </b>Interface layouts were either random or optimized, in which phoneme targets that were likely to be selected together were located in proximity. Target sizes were either static or predictive, such that likely targets were dynamically enlarged following each selection. Communication interfaces were evaluated by 36 users without motor impairments using an alternate access method. Each user was assigned to 1 of 4 interfaces varying in layout and whether prediction was implemented (random/static, random/predictive, optimized/static, optimized/predictive) and participated in 12 sessions over a 3-week period. Six participants with severe motor impairments used both the optimized/static and optimized/predictive interfaces in 1–2 sessions.</div><div><b>Results:</b> In individuals without motor impairments, prediction provided significantly faster communication rates during training (Sessions 1–9), as users were learning the interface target locations and the novel access method. After training, optimization acted to significantly increase communication rates. The optimization likely became relevant only after training when participants knew the target locations and moved directly to the targets. Participants with motor impairments could use the interfaces with alternate access methods and generally rated the interface with prediction as preferred.</div><div><b>Conclusions: </b>Optimization and prediction led to increases in communication rates in users without motor impairments. Predictive interfaces were preferred by users with motor impairments. Future research is needed to translate these results into clinical practice.</div><div><br></div><div><b>Supplemental Material S1.</b> Video showing usage of all four interfaces (random/static; random/predictive; optimized/static; optimized/predictive) to produce messages.</div><div><br></div><div><b>Supplemental Material S2.</b> Survey given to participants with motor impairment following each block of interaction with the interface.</div><div><br></div><div><b>Supplemental Material S3.</b> Results of probes. Top left: Motor task speed. Top right: Visual search speed. Bottom left: phoneme identification speed. Bottom right: phoneme identification accuracy (% correct). Error bars are standard error.</div><div><br></div><div>Cler, G. J., Kolin, K. R., Noordzij, J. P., Jr., Vojtech, J. M., Fager, S. K., & Stepp, C. E. (2019). Optimized and predictive phonemic interfaces for augmentative and alternative communication. <i>Journal of Speech, Language, and Hearing Research, 62</i>, 2065–2081. https://doi.org/10.1044/2019_JSLHR-S-MSC18-18-0187</div><div><br></div><div><b>Publisher Note: </b>This article is part of the Forum: Selected Papers From the 2018 Conference on Motor Speech—Basic Science and Clinical Innovation.</div>