Preface |
|
v | |
|
Chapter 1 Arabic Speech Recognition: Challenges and State of the Art |
|
|
1 | (28) |
|
|
|
|
2 | (1) |
|
2 The Automatic Speech Recognition System Components |
|
|
2 | (8) |
|
2.1 Pronunciation lexicon |
|
|
4 | (1) |
|
|
4 | (4) |
|
|
8 | (1) |
|
|
9 | (1) |
|
3 Literature Review for Arabic ASR |
|
|
10 | (4) |
|
4 Challenges for Arabic ASR Systems |
|
|
14 | (8) |
|
4.1 Using non-diacritized Arabic data |
|
|
15 | (1) |
|
4.2 Speech recognition for Arabic dialects |
|
|
16 | (3) |
|
4.3 Inflection effect and the large vocabulary |
|
|
19 | (3) |
|
5 State of the Art Arabic ASR Performance |
|
|
22 | (2) |
|
|
24 | (5) |
|
|
24 | (5) |
|
Chapter 2 Introduction to Arabic Computational Linguistics |
|
|
29 | (30) |
|
|
|
29 | (1) |
|
2 Layers of Linguistic Analysis |
|
|
30 | (2) |
|
2.1 Phonological analysis |
|
|
30 | (1) |
|
2.2 Morphological analysis |
|
|
31 | (1) |
|
|
31 | (1) |
|
|
31 | (1) |
|
3 Challenges Facing Human Language Technologies |
|
|
32 | (1) |
|
4 Challenges Facing the Arabic Language Processing |
|
|
32 | (4) |
|
|
33 | (1) |
|
|
33 | (1) |
|
4.3 Morphological structure for the Arabic word |
|
|
34 | (1) |
|
4.4 Syntax of the Arabic sentence |
|
|
35 | (1) |
|
5 Defining the Human Languages Technologies |
|
|
36 | (16) |
|
5.1 Texts search (search engines) |
|
|
36 | (2) |
|
|
38 | (1) |
|
|
39 | (1) |
|
5.4 Automated essay scoring |
|
|
39 | (1) |
|
5.5 Automatic text summarization |
|
|
40 | (1) |
|
5.6 Document classification and clustering |
|
|
40 | (1) |
|
|
41 | (1) |
|
5.8 Computer-aided language learning (CALL) |
|
|
42 | (1) |
|
|
42 | (1) |
|
5.10 Automatic speech recognition |
|
|
43 | (2) |
|
5.11 Text to speech (TTS) |
|
|
45 | (1) |
|
5.12 Audio and video search |
|
|
46 | (1) |
|
5.13 Language recognition |
|
|
46 | (1) |
|
5.14 Computer-aided pronunciation learning |
|
|
46 | (1) |
|
5.15 Typewritten optical character recognition (OCR) |
|
|
47 | (1) |
|
5.16 Intelligent character recognition |
|
|
48 | (1) |
|
|
48 | (1) |
|
5.18 Speech to speech translation |
|
|
49 | (1) |
|
5.19 Speech-to-sign-language and sign-language-to-speech |
|
|
49 | (1) |
|
5.20 Dialog management systems |
|
|
50 | (1) |
|
5.21 Advanced information retrieval systems |
|
|
51 | (1) |
|
|
52 | (1) |
|
6 Arabic Computational Linguistics Institutions |
|
|
52 | (5) |
|
6.1 Academic institutions |
|
|
52 | (4) |
|
6.2 Companies interested in computational linguistics |
|
|
56 | (1) |
|
7 Summary and Conclusions |
|
|
57 | (2) |
|
|
57 | (2) |
|
Chapter 3 Challenges in Arabic Natural Language Processing |
|
|
59 | (26) |
|
|
|
|
|
|
59 | (2) |
|
|
61 | (17) |
|
|
62 | (7) |
|
|
69 | (3) |
|
|
72 | (6) |
|
|
78 | (7) |
|
|
79 | (6) |
|
Chapter 4 Arabic Recognition Based on Statistical Methods |
|
|
85 | (26) |
|
|
|
|
85 | (1) |
|
2 A Challenging Morphology |
|
|
86 | (1) |
|
3 Features Extraction Techniques |
|
|
87 | (5) |
|
4 Machine Learning Techniques |
|
|
92 | (2) |
|
|
94 | (9) |
|
5.1 Case 1: Decomposition of the shape/label |
|
|
94 | (2) |
|
5.2 Case 2: Decomposition by association with a model |
|
|
96 | (2) |
|
5.3 Extension of HMM to the Plane |
|
|
98 | (1) |
|
|
99 | (2) |
|
|
101 | (2) |
|
|
103 | (4) |
|
|
107 | (4) |
|
|
108 | (3) |
|
Chapter 5 Arabic Word Spotting Approaches and Techniques |
|
|
111 | (16) |
|
|
|
|
|
111 | (5) |
|
|
112 | (1) |
|
|
113 | (1) |
|
|
114 | (1) |
|
1.4 Word spotting approaches |
|
|
115 | (1) |
|
|
116 | (4) |
|
2.1 Characteristics of Arabic handwriting |
|
|
116 | (2) |
|
2.2 Arabic word spotting approaches |
|
|
118 | (2) |
|
|
120 | (1) |
|
|
121 | (2) |
|
|
123 | (4) |
|
|
123 | (4) |
|
Chapter 6 A `rib --- A Tool to Facilitate School Children's Ability to Analyze Arabic Sentences Syntactically |
|
|
127 | (28) |
|
|
|
|
127 | (3) |
|
|
130 | (1) |
|
3 Basic Arabic Sentences Structure |
|
|
131 | (1) |
|
|
132 | (8) |
|
|
134 | (1) |
|
|
134 | (4) |
|
|
138 | (1) |
|
|
139 | (1) |
|
|
140 | (12) |
|
|
141 | (4) |
|
|
145 | (6) |
|
|
151 | (1) |
|
|
152 | (1) |
|
6 Conclusion and Future Work |
|
|
152 | (3) |
|
|
153 | (2) |
|
Chapter 7 Semi-Automatic Data Annotation, POS Tagging and Mildly Context-Sensitive Disambiguation: The extended Revised AraMorph (XRAM) |
|
|
155 | (14) |
|
|
|
|
|
|
|
|
|
|
|
155 | (1) |
|
|
156 | (9) |
|
2.1 Flag-selectable usage markers |
|
|
157 | (3) |
|
2.2 Probabilistic mildly context-sensitive annotation |
|
|
160 | (1) |
|
2.3 Lexical and morphological XML tagging of texts |
|
|
161 | (2) |
|
2.4 Semi-automatic increment of lexical coverage |
|
|
163 | (2) |
|
3 Validation and Research Grounds |
|
|
165 | (1) |
|
|
166 | (3) |
|
|
166 | (3) |
|
Chapter 8 WeightedNileULex: A Scored Arabic Sentiment Lexicon for Improved Sentiment Analysis |
|
|
169 | (18) |
|
|
|
169 | (1) |
|
|
170 | (2) |
|
|
172 | (1) |
|
4 Assigning Scores to Lexicon Entries |
|
|
173 | (5) |
|
|
173 | (1) |
|
4.2 Collecting term statistics |
|
|
174 | (1) |
|
|
174 | (4) |
|
5 Experiments and Results |
|
|
178 | (6) |
|
5.1 The sentiment analysis system |
|
|
179 | (1) |
|
|
180 | (1) |
|
|
181 | (3) |
|
|
184 | (3) |
|
|
184 | (3) |
|
Chapter 9 Islamic Fatwa Request Routing via Hierarchical Multi-Label Arabic Text Categorization |
|
|
187 | (16) |
|
|
|
|
|
187 | (3) |
|
|
190 | (1) |
|
3 Islamic Fatwa Requests Routing System |
|
|
191 | (4) |
|
|
191 | (2) |
|
|
193 | (1) |
|
|
194 | (1) |
|
|
195 | (4) |
|
|
195 | (2) |
|
|
197 | (1) |
|
4.3 Results and Discussion |
|
|
197 | (2) |
|
5 Future Work and Conclusion |
|
|
199 | (4) |
|
|
200 | (3) |
|
Chapter 10 Arabic and English Typeface Personas |
|
|
203 | (28) |
|
|
|
|
203 | (1) |
|
2 Literature Review of Typeface Personality Studies |
|
|
204 | (3) |
|
3 Arabic Typeface Personality Traits |
|
|
207 | (10) |
|
|
207 | (5) |
|
3.2 Statistical analyses of survey results |
|
|
212 | (5) |
|
4 English Typeface Personality Traits |
|
|
217 | (8) |
|
|
217 | (4) |
|
4.2 Statistical analyses of survey results |
|
|
221 | (4) |
|
5 Summary of English Typefaces |
|
|
225 | (1) |
|
6 Summary of Arabic Typefaces |
|
|
226 | (1) |
|
7 Comparison of Both Studies |
|
|
226 | (1) |
|
8 Conclusions and Future Work |
|
|
227 | (4) |
|
|
228 | (3) |
|
Chapter 11 End-to-End Lexicon Free Arabic Speech Recognition Using Recurrent Neural Networks |
|
|
231 | (18) |
|
|
|
|
|
|
231 | (1) |
|
|
232 | (1) |
|
3 Arabic Speech Recognition System |
|
|
233 | (6) |
|
|
234 | (3) |
|
|
237 | (1) |
|
|
237 | (2) |
|
|
239 | (2) |
|
4.1 Converting the Arabic text to Latin (transliteration process) |
|
|
239 | (1) |
|
4.2 Converting the transcription to alias |
|
|
240 | (1) |
|
4.3 Speech features extraction |
|
|
240 | (1) |
|
|
241 | (4) |
|
5.1 The 8-hour experiment |
|
|
241 | (1) |
|
|
242 | (2) |
|
5.3 The 1200-hour experiment |
|
|
244 | (1) |
|
5.4 The 1200-hour results |
|
|
245 | (1) |
|
|
245 | (4) |
|
|
246 | (3) |
|
Chapter 12 Bio-Inspired Optimization Algorithms for Improving Artificial Neural Networks: A Case Study on Handwritten Letter Recognition |
|
|
249 | (18) |
|
|
|
|
249 | (3) |
|
2 Neural Networks and Bio-inspired Optimization Algorithms |
|
|
252 | (3) |
|
2.1 Neural Networks (NNs) |
|
|
252 | (1) |
|
2.2 Particle Swarm Optimization (PSO) |
|
|
252 | (1) |
|
2.3 Evolutionary Strategy (ES) |
|
|
252 | (1) |
|
2.4 Probability Based Incremental Learning (PBIL) |
|
|
253 | (1) |
|
2.5 Moth-Flame Optimization (MFO) |
|
|
253 | (2) |
|
3 Swarms Working Mechanism |
|
|
255 | (2) |
|
|
257 | (1) |
|
5 Experiments and Results |
|
|
258 | (6) |
|
|
258 | (1) |
|
|
259 | (1) |
|
5.3 Results and discussions |
|
|
259 | (5) |
|
6 Conclusion and Future Work |
|
|
264 | (3) |
|
|
265 | (2) |
Index |
|
267 | |