🧑‍🔬 Ahmed M. Abdelatty Ali

🏛️ Affiliations

🎓Zagazig UniversityZagazig · Egypt2022–2025 · 4 paperscurrent🎓COMSATS University IslamabadIslamabad · Pakistan2013–2025 · 2 paperscurrent🎓Hamad bin Khalifa UniversityDoha · Qatar2015–2024 · 22 papers🏢Analog DevicesNorwood · United States2002–2021 · 16 papersEmployment since 2002🎓University of PennsylvaniaPhiladelphia · United States1995–2003 · 8 papersEducation 1995–1999 · Ph.D.🎓University of EdinburghEdinburgh · United Kingdom2015–2017 · 6 papers🎓Cairo UniversityGiza · Egypt2003–2023 · 4 papers🏢Texas InstrumentsDallas · United States2000–2002 · 3 papersEmployment 2000–2002🎓University of DuhokDuhok · Iraq2020–2024 · 2 papers🏢AppleCupertino · United States2022 · 1 paperEmployment

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 11 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1 2 next →

1. Discriminating between Similar Languages and Arabic Dialect Identification: A Report on the Third DSL Shared Task (2016 · 287 citations)
   The third DSL shared task, held at VarDial 2016 (co-located with COLING 2016), tested how well automatic systems can tell apart closely related languages, language varieties and dialects. It had two subtasks.
2. Findings of the VarDial Evaluation Campaign 2017 (2017 · 261 citations)
   This paper reports on the VarDial 2017 evaluation campaign, held with the fourth VarDial workshop at EACL 2017. It grew out of the earlier DSL shared tasks and broadened them into four separate challenges:
3. Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation Campaign (2018 · 170 citations)
   This report describes the second VarDial Evaluation Campaign, held at the VarDial 2018 workshop alongside COLING 2018. The campaign provides shared benchmarks for NLP on closely related languages, language varieties and dialects. It had five shared tasks.
4. The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition (2016 · 154 citations)
   MGB-2 is a shared evaluation for automatic recognition of Arabic broadcast speech, held for SLT-2016. The earlier English MGB focused on variety across TV genres; this edition focuses on variety across Arabic dialects. The organisers collected about 1,200 hours of Aljazeera TV recordings from 2005–2015, drawn from 19…
5. QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus (2021 · 82 citations)
   The authors tackle the lack of a large Arabic resource that connects speech with NLP-level annotation and covers both Modern Standard Arabic and dialects.
6. Speech Recognition Challenge in the Wild: Arabic MGB-3 (2017 · 78 citations)
   The Arabic MGB-3 Challenge is a shared evaluation that moves Arabic speech recognition from clean broadcast news to dialectal, multi-genre web video.
7. Arabic Speech Recognition by End-to-End, Modular Systems and Human (2021 · 76 citations)
   The paper asks whether machines now match people at transcribing Arabic, a morphologically rich language with mostly undiacritized text and many dialects that lack standard spelling.
8. Automatic Dialect Detection in Arabic Broadcast Speech (2015 · 59 citations)
   The paper tackles automatic identification of Arabic dialects from broadcast speech. It treats this as a harder variant of language identification, since the varieties belong to one language yet differ in lexicon and sound. The authors compare three utterance representations:
9. Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR (2021 · 56 citations)
   The paper asks whether one end-to-end speech recognizer, trained on several languages at once, can cope with how Arabic is actually spoken.
10. MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge (2017 · 37 citations)
    This paper addresses Arabic Dialect Identification (ADI) in the MGB-3 challenge at ASRU 2017. Each Aljazeera news recording must be labelled as Egyptian, Levantine, Gulf, North African or Modern Standard Arabic. The main difficulty is a domain mismatch: the large training set was recorded under different conditions…
11. Advances in dialectal Arabic speech recognition: a study using Twitter to improve Egyptian ASR (2014 · 32 citations)
    The paper tackles automatic speech recognition for Egyptian Arabic. This dialect lacks a fixed spelling standard and has very little transcribed audio. The authors used about 12.5 hours of Egyptian speech drawn from a larger 200-hour Aljazeera broadcast collection: 10 hours for acoustic training and 1.25 hours each…
12. Arabic Code-Switching Speech Recognition using Monolingual Data (2021 · 27 citations)
    The paper tackles Arabic–English code-switching in speech recognition when no mixed-language training material exists.
13. Best Practices for Crowdsourcing Dialectal Arabic Speech Transcription (2015 · 11 citations)
    Dialectal Arabic (DA) has no fixed spelling, so standard crowdsourcing quality checks break down when collecting speech transcripts.
14. Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study (2023 · 9 citations)
    The paper asks whether usable Arabic text-to-speech can be built without a studio corpus by reusing broadcast news collected for ASR.
15. Arabic Retrieval Revisited: Morphological Hole Filling (2012 · 8 citations)
    Arabic search engines depend on stemming. The strongest statistical stemmers still cannot merge singular nouns with their "broken" (internally changed) plurals. They also split named entities whose final letter shifts when a suffix is added. Darwish and Ali address this gap with a character-level transformation model…
16. DARTS: Dialectal Arabic Transcription System (2019 · 7 citations)
    DARTS is a speech-to-text system for Egyptian Arabic, a dialect with very little transcribed audio and no settled spelling conventions.
17. Iqra'Eval: A Shared Task on Qur'anic Pronunciation Assessment (2025 · 6 citations)
    The paper describes Iqra'Eval 2025, the first shared task, which also serves as a publicly available benchmark, targeting the detection and diagnosis of mispronunciations (MDD) in Qur'anic recitation, with MSA-style reading as the case study.
18. Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic (2024 · 5 citations)
    Arabic dialects contain sounds that Modern Standard Arabic spelling does not show (such as the g of Gulf and Egyptian loanwords, or p and v), and the written text often lacks short vowels.
19. Efficient Arabic emotion recognition using deep neural networks (2020 · 5 citations)
    This paper by Yasser Hifny and Ahmed Ali tackles speech emotion recognition for Arabic, a language with few labelled emotional speech resources.
20. Multi-view Dimensionality Reduction for Dialect Identification of Arabic Broadcast Speech (2016 · 5 citations)
    The paper addresses identifying the dialect of spoken Arabic (DID), distinguishing five classes: Modern Standard Arabic (MSA) plus the Egyptian (EGY), Gulf (GLF), North African (NOR) and Levantine (LAV) varieties.
21. Octopus: Towards Building the Arabic Speech LLM Suite (2025 · 2 citations)
    Arabic speech is hard for general audio-language models because of its many dialects, rich morphology, inconsistent spelling and frequent mixing with English.
22. QVoice: Arabic Speech Pronunciation Learning Application (2023 · 2 citations)
    QVoice is a mobile app for practising Arabic pronunciation. It targets two groups: non-native learners, and native speakers whose regional dialect affects their Modern Standard Arabic (MSA). The authors present it as a system demo.
23. DialG2P: Dialectal Grapheme-to-Phoneme. Arabic as a Case Study (2025 · 1 citation)
    The paper addresses grapheme-to-phoneme (G2P) conversion for dialectal Arabic, using Egyptian (EGY) as the test case.
24. FOOCTTS: Generating Arabic Speech with Acoustic Environment for Football Commentator (2023 · 1 citation)
    FOOCTTS is a demo system that turns typed Arabic text into speech in the voice of a Tunisian-dialect football commentator.
25. IQRA 2026: Interspeech Challenge on Automatic Pronunciation Assessment for Modern Standard Arabic (MSA) (2026)
    Arabic mispronunciation detection and diagnosis (MDD) has long lacked open data and comparable evaluation, unlike English or Mandarin.

1 2 next →

All works

30 works of theirs in our library, the most cited first; 27 with a page here, the others link their original until we summarise them.

1. Discriminating between Similar Languages and Arabic Dialect Identification: A Report on the Third DSL Shared TaskInternational Conference on Computational Linguistics (COLING)Shervin Malmasi, Marcos Zampieri, Nikola Ljubešić, et al.2016 · 287 citations
2. Findings of the VarDial Evaluation Campaign 2017Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Marcos Zampieri, Shervin Malmasi, Nikola Ljubešić, et al.2017 · 261 citations
3. Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation CampaignWorkshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Marcos Zampieri, Shervin Malmasi, Preslav Nakov, et al.2018 · 170 citations
4. The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media RecognitionIEEE Spoken Language Technology Workshop (SLT)Ahmed Ali, Peter Bell, James Glass, et al.2016 · 154 citations
5. Word Error Rate Estimation for Speech Recognition: e-WER ↗Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yetAhmed Ali, Steve Renals2018 · 152 citations
6. What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetRamy Baly et al.2020 · 93 citations
7. QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech CorpusAnnual Meeting of the Association for Computational Linguistics (ACL)Hamdy Mubarak, Amir Hussein, Shammur Absar Chowdhury, et al.2021 · 82 citations
8. Speech Recognition Challenge in the Wild: Arabic MGB-3IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Ahmed Ali, Stephan Vogel, Steve Renals2017 · 78 citations
9. Arabic Speech Recognition by End-to-End, Modular Systems and HumanComputer Speech & LanguageAmir Hussein, Shinji Watanabe, Ahmed Ali2021 · 76 citations
10. QCRI advanced transcription system (QATS) for the Arabic Multi-Dialect Broadcast media recognition: MGB-2 challenge ↗IEEE Spoken Language Technology Workshop (SLT) · no summary yetSameer Khurana, Ahmed M. Abdelatty Ali2016 · 67 citations
11. Automatic Dialect Detection in Arabic Broadcast SpeechInterspeechAhmed Ali, Najim Dehak, Patrick Cardinal, et al.2015 · 59 citations
12. Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASRInterspeechShammur Absar Chowdhury, Amir Hussein, Ahmed Abdelali, et al.2021 · 56 citations
13. MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast ChallengeIEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Suwon Shon, Ahmed Ali, James Glass2017 · 37 citations
14. Advances in dialectal Arabic speech recognition: a study using Twitter to improve Egyptian ASRInternational Conference on Spoken Language Translation (IWSLT)Ahmed Ali, Hamdy Mubarak, Stephan Vogel2014 · 32 citations
15. Arabic Code-Switching Speech Recognition using Monolingual DataInterspeechAhmed Ali, Shammur Chowdhury, Amir Hussein, et al.2021 · 27 citations
16. Best Practices for Crowdsourcing Dialectal Arabic Speech TranscriptionWorkshop on Arabic Natural Language ProcessingSamantha Wray, Hamdy Mubarak, Ahmed Ali2015 · 11 citations
17. Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case StudyarXiv:2301.09099Massa Baali, Tomoki Hayashi, Hamdy Mubarak, et al.2023 · 9 citations
18. Arabic Retrieval Revisited: Morphological Hole FillingAnnual Meeting of the Association for Computational Linguistics (ACL)Kareem Darwish, Ahmed Ali2012 · 8 citations
19. DARTS: Dialectal Arabic Transcription SystemarXiv:1909.12163Sameer Khurana, Ahmed Ali, James Glass2019 · 7 citations
20. Iqra'Eval: A Shared Task on Qur'anic Pronunciation AssessmentArabic Natural Language Processing Conference (ArabicNLP)Yassine El Kheir, Amit Meghanani, Hawau Olamide Toyin, et al.2025 · 6 citations
21. Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in ArabicYassine El Kheir, Hamdy Mubarak, Ahmed Ali, et al.Semitic languages · 5 citations
22. Efficient Arabic emotion recognition using deep neural networksarXiv:2011.00346Ahmed Ali, Yasser Hifny2020 · 5 citations
23. Multi-view Dimensionality Reduction for Dialect Identification of Arabic Broadcast SpeecharXiv:1609.05650Sameer Khurana, Ahmed Ali, Steve Renals2016 · 5 citations
24. Octopus: Towards Building the Arabic Speech LLM SuiteArabic Natural Language Processing Conference (ArabicNLP)Sara Althubaiti, Vasista Sai Lodagala, Tjad Clark, et al.2025 · 2 citations
25. QVoice: Arabic Speech Pronunciation Learning ApplicationInterspeechYassine El Kheir, Fouad Khnaisser, Shammur Absar Chowdhury, et al.2023 · 2 citations

See all 30 works by Ahmed M. Abdelatty Ali →

🤝 Co-authors here

12 of 36 co-authors with a page, the most papers together first.

• Hamdy Mubarak ×8
• Shammur Absar Chowdhury ×6
• James Glass ×5
• Amir Hussein ×4
• Steve Renals ×4
• Yassine El Kheir ×4
• Jörg Tiedemann ×3
• Marcos Zampieri ×3
• Nikola Ljubešić ×3
• Preslav Nakov ×3
• Sameer Khurana ×3
• Shervin Malmasi ×3

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×5: ACL 2024, ACL 2021, ACL 2012
• Arabic Natural Language Processing Conference (ArabicNLP) ×4: ArabicNLP 2025 ×4
• Interspeech ×4: Interspeech 2023, Interspeech 2021 ×2, Interspeech 2015
• IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) ×2: ASRU 2017 ×2
• IEEE Spoken Language Technology Workshop (SLT) ×2: SLT 2016
• Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial) ×2: VarDial 2018, VarDial 2017
• International Conference on Computational Linguistics (COLING): COLING 2016
• Computer Speech & Language: Computer Speech & Language 2021
• Conference of the European Chapter of the Association for Computational Linguistics (EACL)
• International Conference on Spoken Language Translation (IWSLT): IWSLT 2014
• Workshop on Arabic Natural Language Processing: Workshop on Arabic Natural Language Processing 2015

🔗 Cited by

Papers of our library cite their works 783 times (of the 149,439 papers whose bibliographies we read); 229 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ahmed-m-abdelatty-ali/