Cross-Word Modeling for Arabic Speech Recognition
Buch in deiner Nähe kaufen
Beschreibung
Cross-Word Modeling for Arabic Speech Recognition utilizes phonological rules in order to model the cross-word problem, a merging of adjacent words in speech caused by continuous speech, to enhance the performance of continuous speech recognition systems. The author aims to provide an understanding of the cross-word problem and how it can be avoided, specifically focusing on Arabic phonology using an HHM-based classifier.
Contents and results will be presented with help of an up-and-running ASR system Examines Arabic phonology, using an HHM-based classifier Uses phonological rules to overcome what is known as the cross-word problem Includes supplementary material: sn.pub/extras
Autor*in
Dia AbuZeina
Themen in »Cross-Word Modeling for Arabic Speech Recognition«
Arabic linguistics Arabic phonological rules Arabic phonology Continuous speech recognition systems Cross-word modeling HHM-based classifier Phonological rules Speech recognition arabic