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.
Reihe
Sprache
Verlagsort
Verlagsgruppe
Illustrationen
14
1 farbige Abbildung, 14 s/w Abbildungen
X, 74 p. 15 illus., 1 illus. in color.
Dateigröße
ISBN-13
978-1-4614-1213-7 (9781461412137)
DOI
10.1007/978-1-4614-1213-7
Schweitzer Klassifikation
An Overview of Speech Recognition Systems.- Arabic Speech Recognition Systems.- The Baseline System.- Cross-Word Pronunciation Variations.- Modeling of Arabic Cross-Word Prononciation Variations.- Performance and Evaluation.
