(function(doc, html, url) {
var widget = doc.createElement("div");
widget.innerHTML = html;
var script = doc.currentScript; // e = a.currentScript;
if (!script) {
var scripts = doc.scripts;
for (var i = 0; i < scripts.length; ++i) {
script = scripts[i];
if (script.src && script.src.indexOf(url) != -1) break;
}
}
script.parentElement.replaceChild(widget, script);
}(document, '
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.
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.