Arabic Phonetic Database
Accurate phonemic and phonetic transcriptions
Includes vowel neutralization and word stress
Learner-friendly romanization system
Overview
CJKI’s Arabic Phonetic Database (APD) provides both phonemic and phonetic transcriptions that accurately indicate how Arabic names and words are pronounced in actual speech. IPA is under construction and is not shown below.
Each of the over 200,000 entries consists of canonical forms without vocalization (as in natural language) and is accompanied by various attributes, such as rich phonological information. This includes the learner-friendly CARS phonemic transcription system, and such unique features as vowel neutralization, word stress, and an indication of velarized vowels.
This resource covers canonical forms only. If you are interested in a fully-inflected Arabic database, please see our Arabic Full-Form Lexicon or ArabLEX.
Arabic Phonetic Database
| POS | Unvocalized | Vocalized | Phonemic (CARS) | Phonetic (IPA) |
|---|---|---|---|---|
| V | قحط | قَحَّط | qáḥḥaṭ | ˈqɑħːɑtˤ |
| V | قطط | قَطَّط | qáṭṭaṭ | ˈqɑtˤːɑtˤ |
| N | قفر | قَفْر | qafr | qɑfr |
| N | قمل | قَمْل | qaml | qɑml |
| N | قريحة | قَرِيحَة | qarī́ḥa | qɑˈrˤɪːħɑ |
| V | قيل | قَيَّل | qáyyal | ˈqɑjːal |
| N | قرى | قِرَى | qíra̱ | ˈqɪrˤɑ |
| N | قصور | قُصُور | quṣū́r | qʊˈsˤʊːrˤ |
| N | قرعة | قُرْعَة | qúrɛa | ˈqʊrˤʕɑ |
| N | رذيلة | رَذِيلَة | radhī́la | rɑˈðiːla |
| V | ربت | رَبَّت | rábbat | ˈrɑbːat |
| N | رغد | رَغْد | raghd | rɑɣd |
| N | ركم | رَكَم | rákam | ˈrɑqɑm |
| V | رنم | رَنَّم | ránnam | ˈrɑnːam |
| V | رثى | رَثَى | rátha̱ | ˈrɑθa |
Practical Applications
APD can be used for such applications as:
Speech synthesis systems
Text-to-speech generation (TTS)
Pedagogical applications
Arabic as a foreign language
Speech recognition systems
Automatic speech recognition (ASR)
Reference Documents
Word Stress and Vowel Neutralization in MSA
Stress and neutralization rules are both linguistically accurate and pedagogically useful, based on how spoken MSA is actually pronounced.
CJKI Arabic Romanization System
An innovative phonemic transcription system developed mainly for ease of use by learners and as an aid to linguists in analyzing the phonological structure of MSA.
Related Resources
Arabic Wordlist
General vocabulary, proper nouns and technical terms
Arabic Full-Form Lexicon
Includes all inflected, declined and conjugated forms
Arabic Phonetic Database
Phonemic transcriptions for core Arabic vocabulary