Archives of Acoustics, 46, 2, pp. 237–247, 2021

Conditional Random Fields Applied to Arabic Orthographic-Phonetic Transcription

National Polytechnic School

National Polytechnic School

Orthographic-To-Phonetic (O2P) Transcription is the process of learning the relationship between the written word and its phonetic transcription. It is a necessary part of Text-To-Speech (TTS) systems and it plays an important role in handling Out-Of-Vocabulary (OOV) words in Automatic Speech Recognition systems. The O2P is a complex task, because for many languages, the correspondence between the orthography and its phonetic transcription is not completely consistent. Over time, the techniques used to tackle this problem have evolved, from earlier rules based systems to the current more sophisticated machine learning approaches. In this paper, we propose an approach for Arabic O2P Conversion based on a probabilistic method: Conditional Random Fields (CRF). We discuss the results and experiments of this method apply on a pronunciation dictionary of the Most Commonly used Arabic Words, a database that we called (MCAW-Dic). MCAW-Dic contains over 35 000 words in Modern Standard Arabic (MSA) and their pronunciation, a database that we have developed by ourselves assisted by phoneticians and linguists from the University of Tlemcen. The results achieved are very satisfactory and point the way towards future innovations. Indeed, in all our tests, the score was between 11 and 15% error rate on the transcription of phonemes (Phoneme Error Rate). We could improve this result by including a large context, but in this case, we encountered memory limitations and calculation difficulties.
Keywords: Orthographic-To-Phonetic Transcription; Conditional Random Fields; text-to-speech; Arabic speech synthesis; Modern Standard Arabic
Full Text: PDF


Abu-Salim I.M. (1988), Consonant assimilation in Arabic: An auto-segmental perspective, Lingua, 74(1): 45–66, doi: 10.1016/0024-3841(88)90048-4.

AbuZeina D., Al-Khatib W., Elshafei M., Al-Muhtaseb H. (2012), Within-word pronunciation variation modeling for Arabic ASRs: a direct data-driven approach, International Journal of Speech Technology, 15(2): 65–75, doi: 10.1007/s10772-011-9122-4.

Ahmed M. E. (1991), Toward an Arabic text-to-speech system, The Arabian Journal for Science and Engineering, 16(4): 565–583.

Al-Daradkah B., Al-Diri B. (2015), Automatic grapheme-to-phoneme conversion of Arabic text, [In:] 2015 Science and Information Conference (SAI), pp. 468–473, doi: 10.1109/SAI.2015.7237184.

Alduais A.M.S. (2013), Quranic phonology and generative phonology: formulating generative phonological rules to non-syllabic Nuun’s Rules, International Journal of Linguistics, 5(5): 33–61, doi: 10.5296/ijl.v5i1.2436.

Al-Ghamdi M., Al-Muhtasib H., Elshafei M. (2004), Phonetic rules in Arabic script, Journal of King Saud University – Computer and Information Sciences, 16: 85–115, doi: 10.1016/S1319-1578(04)80010-7.

Al-Ghamdi M., Elshafei M., Al-Muhtaseb H. (2009), Arabic broadcast news transcription system, International Journal of Speech Technology, 10(4): 183–195, doi: 10.1007/s10772-009-9026-8.

Apostolopoulou M.S., Sotiropoulos D.G., Livieris I.E, Pintelas P. (2009), A memoryless BFGS neural network training algorithm, [In:] Proceeding of the 7th IEEE International Conference on Industrial Informatics (INDIN), pp. 216–221, doi: 10.1109/INDIN.2009.5195806.

Bagshaw P.C. (1998), Phonemic transcription by analogy in text-to-speech synthesis: novel word pronunciation and lexicon compression, Computer Speech and Language, 12(2): 119-142, doi: 10.1006/csla.1998.0042

Biadsy F., Habash N., Hirschberg J. (2009), Improving the Arabic pronunciation dictionary for phone and word recognition with linguistically-based pronunciation rules, [In:] Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, Boulder, Colorado, pp. 397–405.

Casacuberta F., Vidal E. (2007), Systems and tools for machine translation. GIZA ++: Training of statistical translation models, Universitat Politécnica de Valéncia, Spain,

Cherifi E.H. (2020), MCAW-Dict, Phonetic Dictionary of the Most Commonly used Arabic Words with SIMPA Transcription,

Cherifi E.H., Guerti M. (2017), Phonetisaurus-based letter-to-sound transcription for standard Arabic, [In:] The 5th International Conference on Electrical Engineering (ICEE-B 2017), pp. 45–48, October 29th to 31st, 2017, Boumerdes, Algeria, doi: 10.1109/ICEE-B.2017.8192073.

El-Imam Y.A.(1989), An unrestricted vocabulary Arabic speech synthesis system, IEEE Transactions on Acoustics, Speech and Signal Processing, 37(12): 1829–1845, doi: 10.1109/29.45531.

El-Imam Y.A. (2004), Phonetization of Arabic: rules and algorithms, Computer Speech and Language, 18: 339–373, doi: 10.1016/S0885-2308(03)00035-4.

Elshafei M., Al-Ghamdi M., Al-Muhtaseb H., Al-Najjar A. (2008), Generation of Arabic phonetic dictionaries for speech recognition, [In:] Proceedings of the International Conference on Innovations in Information Technology IIT2008, pp. 59-63. doi: 10.1109/INNOVATIONS.2008.4781716

Ferrat K., Guerti M. (2017), An experimental study of the gemination in Arabic language, Archives of Acoustics, 42(4): 571–578, doi: 10.1515/aoa-2017-0061

Habash N., Rambow O., Roth R. (2009), Mada+tokan: a toolkit for Arabic tokenization, diacritization, morphological disambiguation, pos tagging, stemming and lemmatization, [In:] Proceedings of the 2nd International Conference on Arabic Language Resources and Tools (MEDAR), Cairo, Egypt, pp. 102–109.

Illina I., Fohr D., Jouvet D. (2012), Pronunciation generation for proper names using Conditional Random Fields [in French: Génération des prononciations de noms propres à l'aide des Champs Aléatoires Conditionnels], Actes de la Conférence Conjointe JEP-TALN-RECITAL 2012, Vol. 1, pp. 641–648.

Jousse F., Gilleron R., Tellier I., Tommasi M. (2006), Random conditional fields for tree annotation [In French: Champs conditionnels aléatoires pour l'annotation d'arbres], 8e Conférence Francophone Sur L'apprentissage Automatique,

Kudo T. (2005), CRF++: Yet another CRF toolkit. User’s manual and implementation, available at ttp://

Lafferty J., McCallum A., Pereira F. (2001), Conditional Random Fields: probabilistic models for segmenting and labeling sequence data, [In:] Proceedings of the International Conference on Machine Learning ICML'01, pp. 282–289.

Luk R.W.P., Damper R.I. (1996), Stochastic phonographic transduction for English, Computer Speech and Language, 10(2): 133–153, doi: 10.1006/csla.1996.0009.

McCallum A., Li W. (2003), Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons, [In:] Proceedings of the Seventh Conference on Natural Language Learning at {HLT}-{NAACL} 2003, pp. 188–191,

Polyakova T., Bonafonte A. (2005), Main issues in grapheme-to-phonetic transcription for TTS, Procesamiento Del Lenguaje Natural, 2005(35): 29–34,

Priva U.C. (2012), Sign and signal deriving linguistic generalizations from information utility, Phd Thesis, Stanford University.

Ramsay A., Alsharhan I., Ahmed H. (2014), Generation of a phonetic transcription for modern standard Arabic: A knowledge-based model, Computer Speech and Language, 28(4): 959–978, doi: 10.1016/j.csl.2014.02.005.

Roach P. (1987), English Phonetics and Phonology, 3rd ed., Longman: Cambridge UP.

Sejnowsky T., Rosenberg C.R. (1987), Parallel networks that learn to pronounce English text, Complex System, 1(1): 145–168.

Selim H., Anbar T. (1987), A phonetic transcription system of Arabic text, [In:] ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 1446–1449, doi: 10.1109/ICASSP.1987.1169472.

Sha F., Pereira F. (2003), Shallow parsing with conditional random fields, [In:] Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp. 213–220, doi: 10.3115/1073445.1073473.

Sindran F., Mualla F., Haderlein T., Daqrouq K., Nöth E. (2016), Rule-based standard Arabic Phonetization at phoneme, allophone, and syllable level, International Journal of Computational Linguistics (IJCL), 7(2): 23–37.

Sînziana M., Iria J. (2011), L1 vs. L2 regularization in text classification when learning from labeled features, [In:] Proceedings of the 2011 10th International Conference on Machine Learning and Applications, Vol. 1, pp. 168–171, doi: 10.1109/ICMLA.2011.85.

Toutanova K., Klein D., Manning C.D., Singer Y.Y. (2003), Feature-rich part-of-speech tagging with a cyclic dependency network, [In:] Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp. 252–259,

Tsuruoka Y., Tsujii J., Ananiadou S. (2009), Fast full parsing by linear-chain conditional random fields, [In:] Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2009), pp. 790–798,

Van Coile B. (1991), Inductive learning of pronunciation rules with the Depes system, [In:] Proceedings of ICASSP 91: The IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 745–748, doi: 10.1109/ICASSP.1991.150448.

Wallach H. (2002), Efficient training of conditional random fields,; Master's Tthesis, University of Edinburgh.

Wells J.C. (2002), SAMPA for Arabic, OrienTel Project,

Yvon F. (1996), Grapheme-to-phoneme conversion using multiple unbounded overlapping chunks, [In:] Proceedings of the Conference on New Methods in Natural Language Processing, NeMLaP’96, pp. 218–228, Ankara, Turkey.

DOI: 10.24425/aoa.2021.136574

Copyright © Polish Academy of Sciences & Institute of Fundamental Technological Research (IPPT PAN)