Cross-Word Modeling for Arabic Speech Recognition
Springer Science & Business Media, Nov 25, 2011 - Technology & Engineering - 74 pages
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.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
acoustic model Alghamdi algorithm Almuhtasib Arabic broadcast Arabic language Arabic letters Arabic phonetic Arabic speech recognition Audio automatic speech recognition baseline system CMU Sphinx compound words conference on acoustics consonant continuous speech recognition Cross-Word Modeling cross-word problem cross-word pronunciation variation cross-word variations Damma data-driven approach decoding diacritized Elshafei enhanced system errors Fatha feature vector Fosler-Lussier front-end Hamzat Al-Wasl Hidden Markov Model ICASSP IEEE IEEE Trans improvement Kasra knowledge-based laam language model language processing large vocabulary linguistic merging method MFCC modeling cross-word Modeling for Arabic modern standard Arabic MSA phonological rules n-gram neural network Nuun Saakina parameters performance perplexity phoneme phoneme set phonological rules probability Proceedings pronunciation dictionary Pronunciation modeling short vowels shows signal processing speaker speaker-independent speech recognition systems Sphinx Sphinx system SpringerBriefs in Electrical Table Tanween techniques testing set toolkit triphones unvoweled letters within-word variations word error rate workshop