What is it about?
Phonetic transcription helps speech-language pathologists hear and remember speech sound errors their patients make. Unfortunately, it can be very time-consuming to summarize these transcriptions to a score. In this article, we showed how common calculations can be done automatically with the so-called Levenshtein edit distance. We analyzed speech samples from 65 people with aphasia to demonstrate the process.
Featured Image
Photo by Isaac Smith on Unsplash
Why is it important?
Automated calculations agreed very well with manual calculations and were done in a fraction of the time. We recommended that speech-language pathologists and researchers start using the edit distance measure and we shared links to online software for doing the calculations.
Perspectives
It was exciting to develop these resources, because they made it realistic for our research team to conduct large-sample studies of speech production in stroke aphasia and apraxia of speech. It felt good to share resources with our professional communities.
Katarina L Haley
University of North Carolina at Chapel Hill
Read the Original
This page is a summary of: Automating Error Frequency Analysis via the Phonemic Edit Distance Ratio, Journal of Speech Language and Hearing Research, June 2019, American Speech-Language-Hearing Association (ASHA),
DOI: 10.1044/2019_jslhr-s-18-0423.
You can read the full text:
Contributors
The following have contributed to this page
