|
|
In this study the accuracy and reliability of two expedited transcription methods were evaluated for reducing time spent in transcription of narrative language samples elicited from school-age children (7;5-11;10) with developmental language disorder (DLD). Transcription methods included real-time transcription (RTT) from speech language pathologists (SLPs), trained transcribers (TTs), and automatic speech recognition (ASR). Each method was used to transcribe the same 42 language samples, which were compared to reference transcripts produced using traditional transcription. Results indicated non-significant differences in RTT accuracy between SLPs and TTs, while ASR was significantly more accurate than RTT from either source. The reliability of scores produced using each transcription method against the reference transcripts was evaluated on TNU, MLU-words, NDW, NTW and TTR from a SALT Standard Measures Report. Pearson correlations revealed ASR was more reliable than RTT across all 5 metrics. These findings suggest that ASR is a valid and reliable solution for reducing time spent transcribing narrative language samples of school-age children with DLD. This research was funded by the Graduate Research & Creative Opportunities Grant awarded by Utah State University. |
|