(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, '

We present Non-diacritized Arabic speech recognition work based deep learing.

What is it about?

The work makes the machines simulate humans’ behavior for understanding the speech. In other words, it is the process which makes the machine able to convert speech into text. ASR plays an important role in many applications that are used in our daily life

Why is it important?

We investigated the effect of diactrics in Arabic speech recognition based on deep learning. The accuracy and results were decreased after deleting the diacritics from corpus. In addition, the proposed model with nondiacritized transcriptions could achieve a word error rate better than the same model with diacritized transcriptions .

Read more on Kudos…
The following have contributed to this page:
Hamzah Alsayadi
' ,"url"));