An Evaluation of Expedited Transcription Methods for School-Age Children's Narrative Language: Automatic Speech Recognition and Real-Time Transcription.

Purpose This study examined the accuracy and potential clinical utility of two expedited transcription methods for narrative language samples elicited from school-age children (7;5-11;10 [years;months]) with developmental language disorder. Transcription methods included real-time transcription produced by speech-language pathologists (SLPs) and trained transcribers (TTs) as well as Google Cloud Speech automatic speech recognition. Method The accuracy of each transcription method was evaluated against a gold-standard reference corpus. Clinical utility was examined by determining the reliability of scores calculated from the transcripts produced by each method on several language sample analysis (LSA) measures. Participants included seven certified SLPs and seven TTs. Each participant was asked to produce a set of six transcripts in real time, out of a total 42 language samples. The same 42 samples were transcribed using Google Cloud Speech. Transcription accuracy was evaluated through word error rate. Reliability of LSA scores was determined using correlation analysis. Results Results indicated that Google Cloud Speech was significantly more accurate than real-time transcription in transcribing narrative samples and was not impacted by speech rate of the narrator. In contrast, SLP and TT transcription accuracy decreased as a function of increasing speech rate. LSA metrics generated from Google Cloud Speech transcripts were also more reliably calculated. Conclusions Automatic speech recognition showed greater accuracy and clinical utility as an expedited transcription method than real-time transcription. Though there is room for improvement in the accuracy of speech recognition for the purpose of clinical transcription, it produced highly reliable scores on several commonly used LSA metrics. Supplemental Material https://doi.org/10.23641/asha.15167355.

A Systematic Review of Academic Discourse Interventions for School-Aged Children With Language-Related Learning Disabilities.

Purpose This systematic review synthesized a set of peer-reviewed studies published between 1985 and 2019 and addressed the effectiveness of existing narrative and expository discourse interventions for late elementary- and middle school-aged students with language-related learning disabilities. Method A methodical search of the literature for interventions targeting expository or narrative discourse structure for students aged 9-14 years with group experimental designs identified 33 studies, seven of which met specific criteria to be included in this review. Results An 8-point critical appraisal scale was applied to analyze the quality of the study design, and effect sizes were calculated for six of the seven studies; equivocal to small effects of far-transfer outcomes (i.e., generalizability to other settings) and equivocal to moderate near-transfer outcomes (i.e., within the treatment setting) were identified. The most effective intervention studies provided explicit instruction of expository texts with visual supports and student-generated learning materials (e.g., notes or graphic organizers) with moderate dosage (i.e., 180-300 min across 6-8 weeks) in a one-on-one or paired group setting. Greater intervention effects were also seen in children with reading and/or language disorders, compared to children with overall academic performance difficulties. Conclusions A number of expository discourse interventions showed promise for student use of learned skills within the treatment setting (i.e., near-transfer outcomes) but had limited generalization of skills (i.e., far-transfer outcomes). Supplemental Material https://doi.org/10.23641/asha.12449258.