What is it about?
This study tested an automatic speech recognition (ASR) software on the speech of individuals with a motor-speech disorder, primary progressive apraxia of speech. We found that the word error rate (number of errors created by the ASR) correlated with the severity of the motor-speech disorder. However, the ASR transcriptions differed greatly from human-done transcriptions and were unable to distinguish between different subtypes of the motor-speech disorder.
Featured Image
Photo by Jason Leung on Unsplash
Why is it important?
We showed that using ASR systems to determine a word error rate may be clinically significant in determining whether or not a patient may have primary progressive apraxia of speech, a motor-speech disorder and that the word error rate may also be useful for evaluating disease severity. However, ASR cannot substitute human evolution when determining which subtype of primary progressive apraxia of speech a patient may have.
Perspectives
Writing this article with my collaborators was a great pleasure. As it is one of the first papers to evaluate the functionality of ASR systems in motor-speech disorders, specifically primary progressive apraxia of speech, we hope that it inspires future research using this technology within this clinical population.
Katerina Tetzloff
Utah State University
Read the Original
This page is a summary of: Automatic Speech Recognition in Primary Progressive Apraxia of Speech, Journal of Speech Language and Hearing Research, August 2024, American Speech-Language-Hearing Association (ASHA),
DOI: 10.1044/2024_jslhr-24-00049.
You can read the full text:
Contributors
The following have contributed to this page
