Elamur Research⌕
☰
home / papers / 2026 / CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR

CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR

Paper · 2026 · Bashar Talafha, Samar M. Magdy, Aisha Alansari et al.

Summary

Arabic speech recognizers are usually evaluated with dialect labels at the country or broad-region level. That coarse labeling hides the large differences between local communities inside one country. CARDAMOM is a speech corpus built to expose this finer variation. It has about 40 hours of transcribed, mostly unscripted YouTube speech, such as interviews and vlogs. Its recordings span 21 micro-dialects drawn from six countries: Saudi Arabia, Egypt, Lebanon, Jordan, Palestine and Mauritania. Native-speaker co-authors chose the variety inventory and did the annotation. Each utterance carries a transcript, one or more micro-dialect tags, code-switching status and perceived gender.

The authors tested four multilingual ASR systems:

  • Zero-shot: the best system still had 43.47% WER, and it did worst on Mauritanian and Lebanese speech.
  • Adapted: fine-tuning that system on CARDAMOM brought WER down to 35.21%.

A separate audio classifier separated all 21 micro-dialects with 85.57% accuracy, so the labels carry a learnable signal. The corpus is meant as a diagnostic and adaptation benchmark, not a training-scale dataset. It shows which local Arabic varieties current models still serve poorly.

Key points

  • About 40 hours of transcribed speech covering 21 micro-dialects in 6 countries. The 31 native-speaker annotators split as Egypt 5, Jordan 8, Lebanon 2, Mauritania 4, Palestine 3 and Saudi Arabia 9. Annotation was done in Label Studio.
  • Four multilingual ASR systems were benchmarked. The best had 43.47% aggregate WER zero-shot and 35.21% after adaptation on CARDAMOM. Mauritanian and Lebanese varieties were hardest.
  • A dedicated classifier reached 85.57% accuracy on 21-way micro-dialect identification from audio.
  • The release is standoff only: video IDs, timestamps, human transcripts, labels and code to rebuild the audio. No audio is redistributed, and use is limited to non-commercial research.
  • Acknowledged limitations:
    • No inter-annotator agreement is reported, because most segments had only one annotator.
    • Spelling variation in dialect transcription can inflate WER.
    • Source videos may disappear over time.

Interesting ideas

  • I1. The authors label at two levels: one dominant-variety tag per video only organizes collection, while the real labels are per segment and may list several compatible varieties, which avoids forcing one choice on ambiguous material.
  • I2. Near-identical candidate categories were merged before annotation began, which cut label redundancy and made the remaining distinctions easier to apply consistently.
  • I3. The paper recommends spending a double-annotation budget specifically on the most linguistically similar label pairs, since that is where boundary uncertainty lives, instead of re-checking everything.
  • I4. All systems are scored after one shared text normalization pipeline, and the authors admit that legitimate alternative spellings still count as errors; they suggest multi-reference metrics as the fix.
  • I5. Labels are defined as properties of the utterance (what variety is spoken in this clip) rather than of the person, which blocks unintended inferences about who the speaker is or where they live.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (tree): when converting or tagging treebank sentences by English dialect or register, allow several compatible labels per sentence, so ambiguous cases are not misassigned to a single source.
  • I2 (frames): before annotating speech acts or VerbNet roles, merge distinctions that annotators cannot reliably tell apart, so the label set stays explainable and learnable.
  • I3 (learn): when silver data from witness parsers disagrees, send only the most confusable relation or frame pairs to the LLM teacher or a human, which measures label uncertainty cheaply.
  • I4 (tokens): evaluate tokenizer and lemmatizer output against several accepted reference forms (e.g., British/American spellings) after a common normalization, so variant spellings are not counted as errors.
  • I5 (world): keep a strict split between facts about how the text is written (register, dialect, style) and facts about the entities it describes, so the world model never derives entity attributes from surface style.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Hamad bin Khalifa UniversityDoha · Qatar141 works · 14,175 citations🎓University of British ColumbiaVancouver · Canada98 works · 34,805 citations🎓Imperial College LondonLondon · United Kingdom48 works · 12,181 citations🎓American University of BeirutBeirut · Lebanon34 works · 2,561 citations🎓King Fahd University of Petroleum and MineralsDhahran · Saudi Arabia52 works · 4,666 citations🎓Birzeit UniversityBirzeit · Palestine36 works · 798 citations🎓Jordan University of Science and TechnologyIrbid · Jordan15 works · 1,840 citations🎓Taibah UniversityMedina · Saudi Arabia12 works · 64 citations🎓Badr University in CairoCairo · Egypt2 works · 87 citations🎓Imam Abdulrahman Bin Faisal UniversityDammam · Saudi Arabia7 works · 95 citations🎓Lebanese UniversityBeirut · Lebanon4 works · 49 citations🎓Al al-Bayt UniversityAl Mafraq · Jordan2 works · 13 citations

Also on the byline: University of World Economy and Diplomacy · Northern Border University · Southern Company · Institut Supérieur de l'Électronique et du Numérique · Institut Supérieur du Génie Appliqué.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSignal Processing · 452 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 2,908 worksSpeech & spoken language · 480 works

Cite

Cite as Bashar Talafha, Samar M. Magdy, Aisha Alansari, Alaa Alkhawaldeh, Abdurrahman Juma, Sharaf Makahleh, Nour Gamal, Omar Attia, Hanaa Kurdi, Najwa Rizk, Maysa Anaya, Hessah Altimyat, Layal Alhazmi, Shumukh Alotaibi, Hajar Alhadaris, Rayan Alomari, Rahaf Almalaq, Malak Alkhorasani, Sara alghamdi, Rahaf Alshamrani, Nsrin Ashraf, Ibrahim Jaradat, Nada Qardahji, Yasmin Zaraket, Elmoukhtar Brahim, Sidi Ebeidy, Oumoulmouminin Mahmoud, Yahjeb Bouha Khatraty, Meya Haroune, Mohammad Ghaddar, Mohamad Eldirany, Rashed Alamoush, Tala Chhaytle, Nuha Albadi, Yahya El Hadj, Hamzah Luqman, Fadi A. Zaraket, Mustafa Jarrar and Muhammad Abdul-Mageed. 2026. CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR. arXiv:2609.34481.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2609.34481 · arXiv 2609.34481

@misc{talafha2026cardamom,
  title = {{CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR}},
  author = {Bashar Talafha, Samar M. Magdy, Aisha Alansari, Alaa Alkhawaldeh, Abdurrahman Juma, Sharaf Makahleh, Nour Gamal, Omar Attia, Hanaa Kurdi, Najwa Rizk, Maysa Anaya, Hessah Altimyat, Layal Alhazmi, Shumukh Alotaibi, Hajar Alhadaris, Rayan Alomari, Rahaf Almalaq, Malak Alkhorasani, Sara alghamdi, Rahaf Alshamrani, Nsrin Ashraf, Ibrahim Jaradat, Nada Qardahji, Yasmin Zaraket, Elmoukhtar Brahim, Sidi Ebeidy, Oumoulmouminin Mahmoud, Yahjeb Bouha Khatraty, Meya Haroune, Mohammad Ghaddar, Mohamad Eldirany, Rashed Alamoush, Tala Chhaytle, Nuha Albadi, Yahya {El Hadj}, Hamzah Luqman, Fadi A. Zaraket, Mustafa Jarrar and Muhammad Abdul-Mageed},
  year = {2026},
  doi = {10.48550/arxiv.2609.34481},
  eprint = {2609.34481},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2609.34481}
}

References

112 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Hassan R. Abd-el Jawad. 1986. The emergence of an urban dialect in the Jordanian urban centers. International Journal of the Sociology of Language, 61(1):53–64. ↗
  2. Ernest T Abdel-Massih and 1 others. 1979. A comprehensive study of Egyptian Arabic. volume three: A reference grammar of Egyptian Arabic (a preliminary edition). find
  3. Muhammad Abdul-Mageed, Hassan Alhuzali, and Mohamed Elaraby. 2018. You tweet what you speak: A city-level dataset of Arabic dialects. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).
  4. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, and Lyle Ungar. 2020. Toward micro-dialect identification in diaglossic and code-switched environments. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5855–5876, Online. Association for Computational Linguistics. find
  5. Mahmut Ağbaht. 2023. The Arabic Dialect of Šēxtōba/Shaykh Taba (northern Lebanon) in its Regional Context. Ph.D. dissertation, Uppsala University,. find
  6. Maryam Khalifa Al Ali and Hanan Aldarmaki. 2024. Mixat: A data set of bilingual Emirati-English speech. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 222–226, Torino, Italia. ELRA and ICCL. ↗
  7. Aziza Al-Essa. 2022. Arabic interdentals: Variation and linguistic change. Semitic Dialects And Dialectology, page 45. ↗
  8. Mohammad Al-Fetyani, Muhammad Al-Barham, Gheith Abandah, Adham Alsharkawi, and Maha Dawas. 2023. MASC: Massive Arabic speech corpus. In 2022 IEEE Spoken Language Technology Workshop (SLT), pages 1006–1013. find
  9. Areej Al-Hawamdeh. 2015. A Sociolinguistic Investigation of Two Horani Features in Souf, Jordan. Ph.D. thesis, University of Essex, Colchester, UK. Doctoral dissertation. find
  10. Enam Al-Wer. 2003. New dialect formation: The focusing of -kum in Amman. In David Britain and Jenny Cheshire, editors, Social Dialectology: In Honour of Peter Trudgill, pages 59–67. John Benjamins, Amsterdam. find
  11. Enam Al-Wer. 2004. Variability reproduced: A variationist view of interdental outcomes in modern Arabic dialects. In Martine Haak, Rudolf de Jong, and Kees Versteegh, editors, Approaches to Arabic Dialects, pages 21–31. Brill, Leiden and Boston. find
  12. Enam Al-Wer. 2007. The formation of the dialect of Amman: From chaos to order. In Catherine Miller, Enam Al-Wer, Dominique Caubet, and Janet C. E. Watson, editors, Arabic in the City: Issues in Dialect Contact and Language Variation, pages 55–76. Routledge, London. ↗
  13. Enam Al-Wer and Bruno Herin. 2011. The lifecycle of Qaf in Jordan. Langage et Société, (138):59–76. ↗
  14. Enam Al-Wer, Uri Horesh, Bruno Herin, and Maria Fanis. 2015. How Arabic regional features become sectarian features: Jordan as a case study. Zeitschrift für Arabische Linguistik, 62:68–87. find
  15. Al-Wer, Enam. 2002. Jordanian and Palestinian dialects in contact: Vowel raising in Amman. In Mari Jones and Edith Esch, editors, Language Change: The Interplay of Internal, External and Extra-Linguistic Factors, pages 63–79. Mouton de Gruyter, Berlin. ↗
  16. Hanan Aldarmaki and Ahmad Ghannam. 2023. Diacritic recognition performance in Arabic ASR. arXiv preprint arXiv:2302.14022. ↗
  17. Sadeen Alharbi, Areeb Alowisheq, Zoltán Tüske, Kareem Darwish, Abdullah Alrajeh, Abdulmajeed Alrowithi, Aljawharah Bin Tamran, Asma Ibrahim, Raghad Aloraini, Raneem Alnajim, and 1 others. 2024. SADA: Saudi audio dataset for Arabic. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 10286–10290. IEEE. find
  18. Ahmed Ali, Peter Bell, James Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, and Yifan Zhang. 2016. The MGB-2 challenge: Arabic multi-dialect broadcast media recognition. In 2016 IEEE Spoken Language Technology Workshop (SLT), pages 279– 284. IEEE.
  19. Ahmed Ali, Walid Magdy, Peter Bell, and Steve Renais. 2015. Multi-reference WER for evaluating ASR for languages with no orthographic rules. In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pages 576–580. IEEE. find
  20. Ahmed Ali, Suwon Shon, Younes Samih, Hamdy Mubarak, Ahmed Abdelali, James Glass, Steve Renals, and Khalid Choukri. 2019. The MGB-5 challenge: Recognition and dialect identification of dialectal Arabic speech. In 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1026–1033. IEEE. find
  21. Ahmed Ali, Stephan Vogel, and Steve Renals. 2017. Speech recognition challenge in the wild: Arabic MGB-3. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 316–322. IEEE.
  22. Lamya Alkanhal, Abeer Alessa, Elaf Almahmoud, and Rana Alaqil. 2023. Aswat: Arabic audio dataset for automatic speech recognition using speech-representation learning. In Proceedings of Arabic-NLP 2023, pages 120–127, Singapore (Hybrid). Association for Computational Linguistics.
  23. Ammar Mohammed Ali Alqadasi, Akram M Zeki, Mohd Shahrizal Sunar, Siti Zaiton Mohd Hashim, Md Sah hj Salam, and Rawad Abdulghafor. 2025. Arabic dialects speech corpora: A systematic review. Speech Communication, page 103322. find
  24. K. Alqahtani. 2015. A sociolinguistic study of the Tihami Qahtani dialect in Asir. University of Essex Repository. find
  25. Hamzah A Alsayadi, Abdelaziz A Abdelhamid, Islam Hegazy, Bandar Alotaibi, and Zaki T Fayed. 2022. Deep investigation of the recent advances in dialectal Arabic speech recognition. IEEE access, 10:57063– 57079. ↗
  26. Yahya M. Asiri. 2009. Aspects of the Phonology and Morphology of the Rijal Almaa Dialect (South-West Saudi Arabia). Ph.D. thesis, University of Salford. find
  27. Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, and 1 others. 2023. Seamless: Multilingual expressive and streaming speech translation. arXiv preprint arXiv:2312.05187. ↗
  28. Peter Behnstedt and Manfred Woidich. 2018. The formation of the Egyptian Arabic dialect area. Arabic historical dialectology: Linguistic and sociolinguistic approaches, pages 64–95. Jean Cantineau. Course in Arabic phonetics: Followed by general notions of phonetics and phonology. ↗
  29. Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, and 1 others. 2021. GigaSpeech: An evolving, multi-domain ASR corpus with 10,000 hours of transcribed audio. In Proc. Interspeech 2021. find
  30. Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Kai Yu, Chunyu Qiang, Chen Zhang, and Xie Chen. 2026. Habibi: Laying the open-source foundation of unified-dialectal Arabic speech synthesis. arXiv preprint arXiv:2601.13802. ↗
  31. Alex Choux, Marko Avila, Josep Crego, Fethi Bougares, and Antoine Laurent. 2025. TuniFra: A Tunisian Arabic speech corpus with orthographic transcriptions and French translations. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 64–68, Suzhou, China. Association for Computational Linguistics.
  32. David Cohen and Mohammad el Chennafi. 1963. Le dialecte Arabe, H.assānı̄ya de mauritanie: parler de la g@bla. (No Title). find
  33. William M. Cotter. 2022. The Arabic dialect of Gaza city. Journal of the International Phonetic Association, 52(1):122–134. find
  34. William M. Cotter and Uri Horesh. 2015. Social integration and dialect divergence in coastal Palestine. Journal of Sociolinguistics, 19(4):460–483. ↗
  35. Stuart Davis. 1995. Emphasis spread in Arabic and grounded phonology. Linguistic Inquiry, 26(3):465– 498. find
  36. Destination KSA. 2023. Hejaz through history. Accessed: 2025-08-19. find
  37. James Dickins and Janet C. E. Watson. 2001. The representation of palatal vocoids, and palatalization of k in dialects of Arabic. Roehampton Institute London Working Papers in Linguistics, 1:97–124. find
  38. Amirbek Djanibekov, Hawau Olamide Toyin, Raghad Alshalan, Abdullah Alatir, and Hanan Aldarmaki. 2025. Dialectal coverage and generalization in Arabic speech recognition. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29490– 29502, Vienna, Austria. Association for Computational Linguistics. ↗
  39. Abbas El-Tonsi. 1987. A Comprehensive Study of Egyptian Arabic. Volume Three: A Reference Grammar of Egyptian Arabic (a Preliminary Edition). American University in Cairo, Arabic Language Institute. find
  40. Haroun Elleuch, Salima Mdhaffar, Yannick Estève, and Fethi Bougares. 2025. ADI-20: Arabic dialect identification dataset and models. arXiv preprint arXiv:2511.10070. ↗
  41. Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, William T Freeman, and Michael Rubinstein. 2018. Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Transactions on Graphics (TOG), 37(4):1–11. ↗
  42. Louis Léon César Faidherbe. 1887. Langues sénégalaises: wolof, arabe-hassania, soninké, sérère: notions grammaticales, vocabulaires et phrases. E. Leroux. find
  43. Amany Fashwan and Sameh Alansary. 2025. Computational linguistic approach to orthographic representation of Egyptian Arabic: Challenges and implications. ACM Transactions on Asian and Low-Resource Language Information Processing, 24(9):1–14. ↗
  44. Timothy P Francis and Stephen Hanchey. 1979. Mauritanian Arabic. grammar handbook. peace corps language handbook series. find
  45. Hassan AH Gadalla. 2000. Comparative Morphology of Standard and Egyptian Arabic, volume 5. Lincom Europa Munich. find
  46. Marie-Aimée Germanos. 2009. Représentations linguistiques et contact dialectal: remarques sur l’évolution de variantes régionales à Beyrouth. Ph.D. dissertation, Université de la Sorbonne Nouvelle – Paris III. Supervised by Jérôme Lentin. find
  47. Gulf Arabic Resources. 2023. What you need to know about switching dialects. Accessed: 2025-09-03. find
  48. Karim El Haff, Mustafa Jarrar, Tymaa Hammouda, and Fadi Zaraket. 2022. Curras + Baladi: Towards a Levantine Corpus. In Proceedings of the International Conference on Language Resources and Evaluation(LREC 2022), pages 769–778, Marseille, France. European Language Resources Association. ↗
  49. Injy Hamed, Fadhl Eryani, David Palfreyman, and Nizar Habash. 2024. ZAEBUC-spoken: A multilingual multidialectal Arabic-English speech corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17770– 17782, Torino, Italia. ELRA and ICCL.
  50. Stephen Hanchey and Timothy P Francis. 1979. Mauritanian Arabic. communication and culture handbook. peace corps language handbook series. find
  51. Omar Sidi Mohamed Hayballah. 2024. Āma‘ı̄t.: Madkhal ilā Mu'jam al-H . assāniyya. Diwan al-Shanaqitah; Darat Najibawayh al-'Urfiyya. find
  52. Jeffrey Heath. 2003. Hassaniya Arabic (Mali): Poetic and Ethnographic Texts, volume 31. Otto Harrassowitz Verlag. find
  53. Jeffrey Heath. 2004. Hassaniya Arabic (Mali)-English-French Dictionary, volume 33. Otto Harrassowitz Verlag. find
  54. Bruno Herin. 2010. Le parler arabe de Salt (Jordanie). Ph.D. thesis, Université Libre de Bruxelles, Brussels. Doctoral dissertation. find
  55. Bruno Herin. 2014. The dialect of Salt. Encyclopedia of Arabic Language and Linguistics (Online). Leiden, The Netherlands: Brill. find
  56. Bruno Herin and Enam Al-Wer. 2013. From phonological variation to grammatical change: Depalatalisation of /č/ in Salti. In Clive Holes and Rudolf De Jong, editors, Ingham of Arabia: A collection of articles presented as a tribute to the career of Bruce Ingham, pages 55–73. Brill, Leiden. ↗
  57. Bruno Herin, Igor Younes, Enam Al-Wer, and Youssef Al-Sirour. 2022. The classification of bedouin Arabic: Insights from northern Jordan. Languages, 7(1):1–10. ↗
  58. Clive Holes. 2004. Modern Arabic: Structures, Functions, and Varieties. Georgetown University Press. find
  59. Bruce Ingham. 1994. Najdi Arabic: Central Arabian, volume 1 of London Oriental and African Language Library. John Benjamins Publishing Company, Amsterdam and Philadelphia. find
  60. Mustafa Jarrar, Nizar Habash, Diyam Akra, and Nasser Zalmout. 2014. Building a Corpus for Palestinian Arabic: a Preliminary Study. In Proceedings of the EMNLP 2014, Workshop on Arabic Natural Language, pages 18–27. Association For Computational Linguistics.
  61. Mustafa Jarrar, Nizar Habash, Faeq Alrimawi, Diyam Akra, and Nasser Zalmout. 2017. Curras: An Annotated Corpus for the Palestinian Arabic Dialect. Journal Language Resources and Evaluation, 51(3):2-s2.0-85001544989. ↗
  62. Mustafa Jarrar, Fadi Zaraket, Tymaa Hammouda, Daanish Masood Alavi, and Martin Waahlisch. 2023. Lisan: Yemeni, Irqi, Libyan, and Sudanese Arabic Dialect Copora with Morphological Annotations. In The 20th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA), pages 1–7. IEEE. find
  63. Charles Joukhadar. 2023. The social distribution of non-verbal negation in the Lebanese Arabic of Zgharta. Journal of Arabic Sociolinguistics, 1(1):26–49. ↗
  64. Karima Kadaoui, Maryam Al Ali, Hawau Olamide Toyin, Ibrahim Mohammed, and Hanan Aldarmaki. 2024. PolyWER: A holistic evaluation framework for code-switched speech recognition. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6144–6153, Miami, Florida, USA. Association for Computational Linguistics. find
  65. Amr Keleg, Sharon Goldwater, and Walid Magdy. 2023. ALDi: Quantifying the Arabic level of dialectness of text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10597–10611.
  66. Gil Keren, Artyom Kozhevnikov, Yen Meng, Christophe Ropers, Matthew Setzler, Skyler Wang, Ife Adebara, Michael Auli, Can Balioglu, Kevin Chan, and 1 others. 2025. Omnilingual ASR: Open-source multilingual speech recognition for 1600+ languages. arXiv e-prints, pages arXiv–2511. find
  67. Geoffrey Khan, Michael P Streck, and Janet CE Watson. 2011. The Semitic languages: An international handbook, volume 36. Walter de Gruyter. find
  68. Houssam Eddine-Othman Lachemat, Abbas Akli, Nourredine Oukas, Yassine El Kheir, Samia Haboussi, and Shammur Absar Chowdhury. 2025. CAFE: Spontaneous code-switching speech dataset in Algerian dialect, French and English. Data in Brief, 63:112150. find
  69. Jérôme Lentin. 2018. The levant. In Clive Holes, editor, Arabic Historical Dialectology: Linguistic and Sociolinguistic Approaches, Oxford Studies in Diachronic and Historical Linguistics. Oxford University Press, Oxford. find
  70. Marie-Bernard. 1893. Méthode d’arabe parlé (idiome du Sénégal). Imprimerie nationale, Paris. 2 vols. find
  71. Catherine Miller. 2005. Between accomodation and resistance: Upper Egyptian migrants in Cairo. Linguistics, 399:903. ↗
  72. Amany Hamed Mohamed. 2024. Distinctive linguistic features of Egyptian-Arabic dialect of farafra oasis: The problem of local identity. Wadi El-Nile Journal for Humanitarian, Social and Educational Studies, 41(41):37–80. ↗
  73. Mai Mohamed Eida and Nizar Habash. 2025. Beyond Cairo: Sa’idi Egyptian Arabic literary corpus construction and analysis. In Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 292–304, Albuquerque, USA. Association for Computational Linguistics.
  74. Hamdy Mubarak, Amir Hussein, Shammur Absar Chowdhury, and Ahmed Ali. 2021. QASR: QCRI aljazeera speech resource a large scale annotated Arabic speech corpus. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2274–2285. ↗
  75. Amina Naciri-Azzouz. 2023. A brief overview of national languages in mauritania. Africana Studia, (40):93–102. ↗
  76. Amal Nayouf, Tymaa Hammouda, Mustafa Jarrar, Fadi Zaraket, and Mohamad-Bassam Kurdy. 2023. Nâbra: Syrian Arabic Dialects with Morphological Annotations. In Proceedings of the 1st Arabic Natural Language Processing Conference (ArabicNLP), Part of the EMNLP 2023, pages 12–23. ACL. ↗
  77. Sidi Ahmed Ould al Amir. Qirā'a fı̄ kitāb “āma‘ı̄t.: Madkhal ilā mu'jam al-h.assāniyya”. Scribd. Review of the book Āma‘ı̄t.: Madkhal ilā Mu'jam al-H.assāniyya. Accessed: 2026-05-21. find
  78. Ömer Tarik Özyilmaz, Matt Coler, and Matias Valdenegro-Toro. 2025. Overcoming data scarcity in multi-dialectal Arabic ASR via Whisper fine-tuning. arXiv preprint arXiv:2506.02627. ↗
  79. David S Pallett. 2003. A look at nist’s benchmark asr tests: past, present, and future. In 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No. 03EX721), pages 483–488. IEEE. find
  80. Heikki Palva. 1984. A general classification for the Arabic dialects spoken in Palestine and Transjordan. Studia Orientalia, 55:357–376. find
  81. Heikki Palva. 2008. Northwest Arabian Arabic. In Kees Versteegh, Mushira Eid, Alaa Elgibali, Manfred Woidich, and Andrzej Zaborski, editors, Encyclopedia of Arabic Language and Linguistics. Brill, Leiden. find
  82. Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, and 1 others. 2024. Scaling speech technology to 1,000+ languages. Journal of Machine Learning Research, 25(97):1–52.
  83. Stephan Procházka. 2021. Arabic dialectology. In Karin Ryding and David Wilmsen, editors, The Cambridge Handbook of Arabic Linguistics, Cambridge Handbooks in Language and Linguistics, pages 214– 243. Cambridge University Press. find
  84. Theodore Jr. Prochazka. 1988. Saudi Arabian Dialects. Library of Arabic Linguistics, Monograph No. 8. Kegan Paul International / Routledge (Taylor & Francis Group), London and New York. find
  85. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning, pages 28492–28518. PMLR. ↗
  86. Albert Reynier. 1909. Méthode pour l’étude du dialecte maure. imp. lith. A. Beau fils & Cie. find
  87. Mohammad Salameh, Houda Bouamor, and Nizar Habash. 2018. Fine-grained Arabic dialect identification. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1332– 1344, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
  88. Ameerah Zubair Sambas. 2016. The Hijazi dialect in the light of popular proverbs: A linguistic study. Philology, 33(65):71–102. find
  89. Soha B. Sandouka and Yousef A. Alotaibi. 2021. Extended rhythm-based investigation of Saudi dialects using the Saudi accented Arabic voice bank corpus. In 2020 International Conference on Communications, Signal Processing, and their Applications (ICC-SPA), pages 1–5. find
  90. SEAMLESS Communication Team. 2025. Joint speech and text machine translation for up to 100 languages. Nature, 637:587–593. ↗
  91. Valentina Serreli and 1 others. 2019. Perceptual dialectology of Egypt. a view from the Berber-speaking periphery. In Studies on Arabic Dialectology and Sociolinguistics Proceedings of the 12th International Conference of AIDA held in Marseille from May 30th to June 2nd 2017. Institut de recherches et d’études sur les mondes arabes et musulmans. find
  92. Kimary N. Shahin. 2008. Palestinian Arabic. In Kees Versteegh, Mushira Eid, Alaa Elgibali, Manfred Woidich, and Andrzej Zaborski, editors, Encyclopedia of Arabic Language and Linguistics, pages 526–538. Brill, Leiden. find
  93. Hagen Soltau, George Saon, Brian Kingsbury, Hong-Kwang Jeff Kuo, Lidia Mangu, Daniel Povey, and Ahmad Emami. 2009. Advances in Arabic speech transcription at IBM under the DARPA GALE program. IEEE transactions on audio, speech, and language processing, 17(5):884–894. ↗
  94. Christopher Stone. 2008. Popular Culture and Nationalism in Lebanon: The Fairouz and Rahbani Nation. Routledge Studies in Middle Eastern Literatures. Routledge, London and New York. find
  95. Peter Sullivan, AbdelRahim Elmadany, Alcides Alcoba Inciarte, and Muhammad Abdul-Mageed. 2026. Arab voices: Mapping standard and dialectal Arabic speech technology. arXiv preprint arXiv:2601.13319. ↗
  96. Catherine Taine-Cheikh. 2007. Hassâniyya Arabic. In M. Eid, A. Elgibali, K. Versteegh (editor-in chief), and M. Woidich & A. Zaborski, editors, Encyclopedia of Arabic Language and Linguistics (EALL), vol. 2 II (Eg-Lan), pages 240–250. Brill. find
  97. Catherine Taine-Cheikh. 2018. H.assāniyya Arabic in Contact with Berber: The Case of Quadriliteral Verbs. Arabic in Contact, 6:136–159. find
  98. Catherine Taine-Cheikh. 2020. H.assāniyya Arabic. Arabic and Contact-Induced Change, 1:245. find
  99. Bashar Talafha, Amin Abu Alhassan, and Muhammad Abdul-Mageed. 2025. Context-aware Whisper for Arabic ASR under linguistic varieties. arXiv preprint arXiv:2511.18774. ↗
  100. Bashar Talafha, Karima Kadaoui, Samar Mohamed Magdy, Mariem Habiboullah, Chafei Mohamed Chafei, Ahmed Oumar El-Shangiti, Hiba Zayed, Mohamedou Cheikh Tourad, Rahaf Alhamouri, Rwaa Assi, and 1 others. 2024. Casablanca: Data and models for multidialectal Arabic speech recognition. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21745–21758.
  101. Bashar Talafha, Abdul Waheed, and Muhammad Abdul-Mageed. 2023. N-shot benchmarking of Whisper on diverse Arabic speech recognition. arXiv preprint arXiv:2306.02902. ↗
  102. Maxim Tkachenko, Mikhail Malyuk, Andrey Holmanyuk, and Nikolai Liubimov. 2020. Label studio: Data labeling software. Open source software available from https://github.com/heartexlabs/labelstudio, 2022. ↗
  103. Hawau Toyin, Rufael Marew, Humaid Alblooshi, Samar M Magdy, and Hanan Aldarmaki. 2025. Ar-Voice: A multi-speaker dataset for Arabic speech synthesis. In Proc. Interspeech 2025, pages 4808– 4812. find
  104. Hawau Olamide Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, and Hanan Aldarmaki. 2023. ArTST: Arabic text and speech transformer. In Proceedings of ArabicNLP 2023, pages 41–51, Singapore (Hybrid). Association for Computational Linguistics.
  105. Abu Ulbah and Ateya Mohammed. 2024. The adverb of time (now) in the Palestinian dialect. a grammatical-lexical study. Al-Majma: Studies in Arabic Language, Literature & Thought, (19). find
  106. Jörgen Valk and Tanel Alumäe. 2021. Voxlingua107: a dataset for spoken language recognition. In 2021 IEEE Spoken Language Technology Workshop (SLT), pages 652–658. IEEE. find
  107. Abdul Waheed, Bashar Talafha, Peter Sullivan, Abdel-Rahim Elmadany, and Muhammad Abdul-Mageed. 2023. VoxArabica: A robust dialect-aware Arabic speech recognition system. In Proceedings of ArabicNLP 2023, pages 441–449.
  108. Yingzhi Wang, Anas Alhmoud, and Muhammad Alqurishi. 2025. Open universal Arabic ASR leaderboard. In Proceedings of Interspeech 2025, pages 1168– 1172.
  109. Janet CE Watson. 2002. The Phonology and Morphology of Arabic. OUP Oxford. ↗
  110. Manfred Woidich. 1996. Rural dialect of Egyptian Arabic: An overview. Égypte/Monde arabe, (27-28):325–354. ↗
  111. Islam Youssef. 2021. Contrastive feature typologies of Arabic consonant reflexes. Languages, 6(3):141. ↗
  112. Omar F Zaidan and Chris Callison-Burch. 2014. Arabic dialect identification. Computational Linguistics, 40(1):171–202. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/talafha-2026-cardamom-micro-dialectal-arabic-speech/