Elamur Research⌕
☰
home / papers / 2026 / NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task

NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task

Paper · 2026 · Peter Sullivan, Bashar Talafha, Ahmed Ashraf et al.

Summary

NADI 2026 is the seventh round of the NADI series and the second focused on spoken dialectal Arabic. It targets a mismatch: benchmarks tend to use clean, in-domain recordings of a few varieties, while real systems face poor audio, speakers whose variety is not known, mid-utterance language switching and unfamiliar domains. The organizers built five tasks with eight subtasks. ASR has three: low-bandwidth, mixed-dialect and Tunisian code-switched. The other tasks are out-of-domain spoken dialect identification (SDID), and three that are new to the series: TTS, dialect-to-English SLT, and SLU with unseen domains. Each task is posed under a distribution shift. Twenty-one teams took part.

The main lesson is that out-of-domain generalization is still the hardest part. Dialect identification accuracy falls sharply outside the training domain. Arabic-specialized foundation models, multimodal identification and system combination did best. The benchmark gives a more honest picture of how dialect-aware Arabic speech technology performs.

Key points

  • Scale: 21 teams from at least 13 countries, 48 test-phase submissions (41 valid) and 14 system papers. This ties NADI 2022 for the most teams. All subtasks except TTS ran on Codabench.
  • SDID baseline: accuracy drops from 81.19% in-domain to 28.70% out-of-domain, and the best team reached only 56.15%. The test set covers six countries and 18 city dialects, and its label inventory was hidden from participants.
  • Robust ASR data: unreleased Casablanca audio, downsampled to 4 kHz and then upsampled to 16 kHz to imitate weak connections.
  • Code-switched ASR: three very different systems finished within 0.12 WER of each other:
    • a fully finetuned 2B encoder–decoder,
    • a LoRA model training 3.6% of the parameters of its closest rival,
    • a ten-system ROVER ensemble.
  • Spelling variation: merging hamza variants cuts the top-five WER by 0.29 points (about 2%) without changing the ranking. The authors treat this as a lower bound on spelling-related error. SLT used WhiteHouse evaluation data.

Interesting ideas

  • I1. Robustness is measured by deliberately degrading the input (bandwidth loss) instead of collecting new noisy data, so clean and degraded scores on the same items can be compared directly.
  • I2. Hiding the label set at test time stops systems from exploiting knowledge of which classes can appear.
  • I3. The authors measure how much of the metric is artifact by normalizing one kind of orthographic variation and checking whether the rankings move.
  • I4. Whole application domains were kept out of development data, so the test checks transfer to new domains rather than interpolation.
  • I5. The organizers ask whether a routing step (dialect ID before ASR) actually helps compared with one general model, and propose testing both pipelines directly.

For Mova

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

  • I1 (tree): Run the parser on corrupted copies of treebank sentences (no punctuation, lowercase, typos) and report the LAS gap as a robustness score.
  • I2 (frames): Evaluate role and speech-act labeling on texts whose frame inventory is not announced, to check that the labeler does not lean on a known closed set.
  • I3 (tokens): Score lemma and tagger accuracy before and after folding spelling variants (British/American, hyphenation), so real errors are separated from harmless variation.
  • I4 (answer): Hold out entire genres (for example, fables versus school tests) when evaluating the readers, to see whether answers come from understanding or from genre habits.
  • I5 (tree): Compare routing sentences to dialect-converted treebank models against a single unified gparse model, so the dialect-conversion stage has to justify itself.

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

 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 Peter Sullivan, Bashar Talafha, Ahmed Ashraf, Fethi Bougares, Haroun Elleuch, Chiyu Zhang, AbdelRahim Elmadany, Youssef Mohamed, Salima Mdhaffar, Yannick Esteve, Mohamed Elhoseiny, Hamzah Luqman, Nizar Habash and Muhammad Abdul-Mageed. 2026. NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task. arXiv:2609.27086.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2609.27086 · arXiv 2609.27086

@misc{sullivan2026nadi,
  title = {{NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task}},
  author = {Peter Sullivan, Bashar Talafha, Ahmed Ashraf, Fethi Bougares, Haroun Elleuch, Chiyu Zhang, AbdelRahim Elmadany, Youssef Mohamed, Salima Mdhaffar, Yannick Esteve, Mohamed Elhoseiny, Hamzah Luqman, Nizar Habash and Muhammad Abdul-Mageed},
  year = {2026},
  doi = {10.48550/arxiv.2609.27086},
  eprint = {2609.27086},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2609.27086}
}

References

140 references, 55 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mohamed Abdelazi, Fatimah Mohamed Emad Elden, Mousa Ashraf Abd El Malak, and Omer Nacar. 2026. NAMAA Community at NADI 2026: Mixed-Dialect and Code-Switched Arabic ASR and Spoken Dialect Identification. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  2. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2021. ARBERT & MARBERT: Deep bidirectional transformers for Arabic. 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 7088–7105, Online. Association for Computational Linguistics. ↗
  3. Muhammad Abdul-Mageed, AbdelRahim Elmadany, Chiyu Zhang, El Moatez Billah Nagoudi, Houda Bouamor, and Nizar Habash. 2023. NADI 2023: The fourth nuanced Arabic dialect identification shared task. In Proceedings of ArabicNLP 2023, pages 600– 613, Singapore (Hybrid). Association for Computational Linguistics. https://alliancecan.ca ↗
  4. Muhammad Abdul-Mageed, Amr Keleg, AbdelRahim Elmadany, Chiyu Zhang, Injy Hamed, Walid Magdy, Houda Bouamor, and Nizar Habash. 2024. NADI 2024: The fifth nuanced Arabic dialect identification shared task. In Proceedings of the Second Arabic Natural Language Processing Conference, pages 709–728, Bangkok, Thailand. Association for Computational Linguistics.
  5. Muhammad Abdul-Mageed, Chiyu Zhang, Houda Bouamor, and Nizar Habash. 2020. NADI 2020: The first nuanced Arabic dialect identification shared task. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, WANLP@COLING 2020, Barcelona, Spain (Online), December 12, 2020, pages 97–110. Association for Computational Linguistics. ↗
  6. Muhammad Abdul-Mageed, Chiyu Zhang, AbdelRahim Elmadany, Houda Bouamor, and Nizar Habash. 2022. NADI 2022: The third nuanced Arabic dialect identification shared task. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 85–97, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  7. Muhammad Abdul-Mageed, Chiyu Zhang, Abdel-Rahim A. Elmadany, Houda Bouamor, and Nizar Habash. 2021. NADI 2021: The second nuanced Arabic dialect identification shared task. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, WANLP 2021, Kyiv, Ukraine (Virtual), April 9, 2021, pages 244–259. Association for Computational Linguistics. ↗
  8. Badr M. Abdullah, Matthew Baas, Bernd Möbius, and Dietrich Klakow. 2025. Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification. In Interspeech 2025, pages 2790– 2794.
  9. Idris Abdulmumin, Victor Agostinelli, Tanel Alumäe, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Claudia Borg, Fethi Bougares, Roldano Cattoni, Mauro Cettolo, Lizhong Chen, William Chen, Raj Dabre, Yannick Estève, Marcello Federico, Mark Fishel, Marco Gaido, Dávid Javorský, Marek Kasztelnik, and 33 others. 2025. Findings of the IWSLT 2025 evaluation campaign. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 412–481, Vienna, Austria (in-person and online). Association for Computational Linguistics. find
  10. Mohammad Al-Fetyani, Muhammad Al-Barham, Gheith A. Abandah, Adham Alsharkawi, and Maha Dawas. 2022. MASC: Massive Arabic speech corpus. In Proceedings of the 2022 IEEE Spoken Language Technology Workshop (SLT), page 1002206. find
  11. Jesujoba O Alabi, Xuechen Liu, Dietrich Klakow, and Junichi Yamagishi. 2024. AfriHuBERT: A self-supervised speech representation model for African languages. arXiv preprint arXiv:2409.20201. ↗
  12. Hatim Alhumid, Naif Alharthi, Elaf S. Alsaedi, Faris Alasmary, Ahmad Ghannam, Anas Adel Salamah, Shouq Sadah, and Lahouari Ghouti. 2026. Abjad AI at NADI 2026 shared task: Overcoming Data Scarcity in Arabic Speech Processing through Augmentation. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  13. 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.
  14. Ahmed Ali, Shammur Chowdhury, Mohamed Afify, Wassim El-Hajj, Hazem Hajj, Mourad Abbas, Amir Hussein, Nada Ghneim, Mohammad Abushariah, and Assal Alqudah. 2021. Connecting Arabs: Bridging the gap in dialectal speech recognition. Communications of the ACM, 64(4):124–129. ↗
  15. 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
  16. 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
  17. 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.
  18. Sulaiman Alkurbi. 2026. Wifaq at NADI 2026 Shared Task: Diversity-Aware System Combination for Robust Arabic ASR. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  19. Ibrahim Almajai. 2026. Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. ↗
  20. Mahmoud Alshrief, Mohamed Bahgat, Mahmoud Zaher, and Sahar Selim. 2026. A Two-Phase Acoustic Fine-Tuning Strategy for Robust Dialectal Arabic Speech Recognition NADI 2026 Subtask 1.1: Noisy Country-Level ASR. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  21. Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, and Furu Wei. 2022. SpeechT5: Unified-modal encoder-decoder pre-training for spoken language processing. Preprint, arXiv:2110.07205. ↗
  22. Rosana Ardila, Megan Branson, Kelly Davis, Michael Kohler, Josh Meyer, Michael Henretty, Reuben Morais, Lindsay Saunders, Francis Tyers, and Gregor Weber. 2020. Common Voice: A massively-multilingual speech corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4218–4222, Marseille, France. European Language Resources Association. ↗
  23. Ahmed Ashraf, Aisha Alansari, Fadel Al Abbas, Nada Almarwani, Samah Aloufi, Saad Ezzini, Maged S. Al-shaibani, Doaa Dalaq, AbdelRahim A. Elmadany, Muhammad Abdul-Mageed, Mohamed Mehdi Trigui, Dania Refai, Layan Refai, Mohamed Akrout, Mustafa Jarrar, Wasfi G. Al-Khatib, Alaa Dalaq, Darin El-Nakla, Samir Abdaljalil, and 14 others. 2026. Bulbul: A dataset for dialectal Arabic speech recognition. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, Budapest, Hungary. Association for Computational Linguistics. To appear.
  24. Atlasia. 2026. MoulSot: A curated Moroccan Darija speech dataset and fine-tuned ASR model. find
  25. Houdaifa Atou, Issam Ait Yahia, and Ismail Berrada. 2026. Lynx at the NADI 2026 Shared Task: Exploring ASR Representations and Transcripts for Dialectal Arabic Speech Understanding. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  26. Matthew Baas, Benjamin van Niekerk, and Herman Kamper. 2023. Voice conversion with just nearest neighbors. In Interspeech 2023, pages 2053–2057. find
  27. Kaito Baba, Wataru Nakata, Yuki Saito, and Hiroshi Saruwatari. 2024. The T05 system for the Voice-MOS Challenge 2024: Transfer learning from deep image classifier to naturalness MOS prediction of high-quality synthetic speech. In IEEE Spoken Language Technology Workshop (SLT), pages 818–824. find
  28. Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, and Michael Auli. 2022. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale. In Interspeech 2022, pages 2278–2282.
  29. Alexei Baevski, Arun Babu, Wei-Ning Hsu, and Michael Auli. 2023. Efficient self-supervised learning with contextualized target representations for vision, speech and language. In International conference on machine learning, pages 1416–1429. PMLR. ↗
  30. Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Advances in Neural Information Processing Systems (NeurIPS), volume 33, pages 12449–12460.
  31. Raphaël Bagat, Irina Illina, and Emmanuel Vincent. 2025. Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition. In Interspeech 2025, pages 1143–1147. find
  32. Loïc Barrault, Yu-An Chung, Mariano Cora Meglioli, David Dale, Ning Dong, Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, and 1 others. 2023a. SeamlessM4T: Massively multilingual & multimodal machine translation. arXiv preprint arXiv:2308.11596. ↗
  33. 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. 2023b. Seamless: Multilingual expressive and streaming speech translation. arXiv preprint arXiv:2312.05187. ↗
  34. Fatma Zahra Besdouri, Inès Zribi, and Lamia Hadrich Belguith. 2024. Arabic automatic speech recognition: challenges and progress. Speech Communication, 163:103110. ↗
  35. Fadi Biadsy, Julia Hirschberg, and Nizar Habash. 2009. Spoken Arabic dialect identification using phonotactic modeling. In Proceedings of the EACL 2009 workshop on computational approaches to semitic languages, pages 53–61.
  36. Astik Biswas, Oleg Shevelev, Amine Abdaoui, Vivek Tyagi, and Abdelmoumene Boumadane. 2025. Adapting Whisper for low-resource Hindi-English code-mix speech with on-the-fly augmentation & LLM-synthesised data. In Interspeech 2025, pages 4293–4297. find
  37. Verena Blaschke, Miriam Winkler, Constantin Förster, Gabriele Wenger-Glemser, and Barbara Plank. 2025. A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation. In Interspeech 2025, pages 913–917.
  38. Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexander Erdmann, and Kemal Oflazer. 2018. The MADAR Arabic dialect corpus and lexicon. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018. European Language Resources Association (ELRA). find
  39. Lallouani Bouchakour, Khaled Lounnas, and Ahmed Krobba. 2025. Enhancing Arabic ASR in noisy and transcoding EVS conditions: A multimodal deep learning study. In FedCSIS (Position Papers), pages 1–8. find
  40. Fethi Bougares, Salima Mdhaffar, Haroun Elleuch, and Yannick Estève. 2025. TEDxTN: A three-way speech translation corpus for code-switched Tunisian Arabic - English. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 278– 287, Suzhou, China. Association for Computational Linguistics.
  41. Fethi Bougares, Salima Mdhaffar, and Yannick Estève. 2026. WhiteHouse: Translation of the Casablanca corpus for multi-dialectal Arabic speech translation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5849–5855, Palma de Mallorca, Spain. ELRA Language Resource Association.
  42. Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, and Julian Weber. 2024. XTTS: a massively multilingual zero-shot text-to-speech model. Preprint, arXiv:2406.04904. ↗
  43. Shaun Cassini, Sebastian Vincent, Xiaolu Lu, Julian Mack, Dhruti Joshi, and Pierre Richemond. 2026. cohere-transcribe-arabic-07-2026 (revision 0a8193c). find
  44. William Chan, Navdeep Jaitly, Quoc Le, and Oriol Vinyals. 2016. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In Proceedings of ICASSP, pages 4960– 4964. find
  45. Chaimae Chellaf, Haroun Elleuch, Othman Istaiteh, D. Fortuné Kponou, Fethi Bougares, Yannick Estève, and Salima Mdhaffar. 2025. LIA and ELYA-DATA systems for the IWSLT 2025 low-resource speech translation shared task. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 274–281, Vienna, Austria (in-person and online). Association for Computational Linguistics. find
  46. Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, and 1 others. 2022. WavLM: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing, 16(6):1505–1518. find
  47. Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, and Xie Chen. 2026. Habibi: Laying the open-source foundation of unified-dialectal Arabic speech synthesis. Preprint, arXiv:2601.13802. ↗
  48. 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.
  49. Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, and Ankur Bapna. 2023. FLEURS: Few-shot learning evaluation of universal representations of speech. In 2022 IEEE Spoken Language Technology Workshop (SLT), pages 798–805. IEEE.
  50. Abdelghani Dahou, Abdelhalim Hafedh Dahou, Mohamed Amine Chéragui, Amin Abdedaiem, Mohammed AA Al-Qaness, Mohamed Abd Elaziz, Ahmed A Ewees, and Zhonglong Zheng. 2025. A survey on dialect Arabic processing and analysis: Recent advances and future trends. ACM Transactions on Asian and Low-Resource Language Information Processing, 24(8):1–45. ↗
  51. Najim Dehak, Pedro A Torres-Carrasquillo, Douglas Reynolds, and Reda Dehak. 2011. Language recognition via i-vectors and dimensionality reduction. In Interspeech 2011, pages 857–860. find
  52. Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck. 2020. ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. In Interspeech 2020, pages 3830–3834. find
  53. Spandan Dey, Md Sahidullah, and Goutam Saha. 2023. Cross-corpora spoken language identification with domain diversification and generalization. Computer Speech & Language, 81:101489. ↗
  54. ElevenLabs. 2023. Eleven Multilingual v2. https://elevenlabs.io/blog/eleven-multilingual-v2. Accessed: Aug. 9, 2026. ↗
  55. Haroun Elleuch, Salima Mdhaffar, Yannick Estève, and Fethi Bougares. 2026a. SLURP-TN : Resource for Tunisian dialect spoken language understanding. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1544–1552, Palma de Mallorca, Spain. ELRA Language Resource Association. ↗
  56. Haroun Elleuch, Salima Mdhaffar, Yannick Estève, and Fethi Bougares. 2025. ADI-20: Arabic Dialect Identification dataset and models. In Interspeech 2025, pages 2775–2779.
  57. Haroun Elleuch, Youssef Saidi, Salima Mdhaffar, Yannick Estève, and Fethi Bougares. 2025. ELYADATA & LIA at NADI 2025: ASR and ADI subtasks. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 762– 766, Suzhou, China. Association for Computational Linguistics.
  58. Haroun Elleuch, Ryan Whetten, Salima Mdhaffar, Yannick Estève, and Fethi Bougares. 2026b. Ara-BEST-RQ: Multi dialectal Arabic SSL. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5326– 5330. IEEE. ↗
  59. Jonathan G Fiscus. 1997. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER). In 1997 IEEE workshop on automatic speech recognition and understanding proceedings, pages 347–354. IEEE. find
  60. Jack FitzGerald, Christopher Hench, Charith Peris, Scott Mackie, Kay Rottmann, Ana Sanchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, Swetha Ranganath, Laurie Crist, Misha Britan, Wouter Leeuwis, Gokhan Tur, and Prem Natarajan. 2023. MASSIVE: A 1M-example multilingual natural language understanding dataset with 51 typologically-diverse languages. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4277–4302, Toronto, Canada. Association for Computational Linguistics. ↗
  61. Xun Gong, Anqi Lv, Wangyou Zhang, Zhiming Wang, Huijia Zhu, and Yanmin Qian. 2025. BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM. In Interspeech 2025, pages 4043–4047. find
  62. Google Cloud. 2026. Gemini-TTS | Cloud Text-to-Speech. https://cloud.google.com/text-to-speech/docs/gemini-tts. Accessed: Aug. 9, 2026. ↗
  63. Alex Graves, Santiago Fernández, Faustino Gomez, and Jürgen Schmidhuber. 2006. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on Machine learning, pages 369–376. find
  64. Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, and Ruoming Pang. 2020. Conformer: Convolution-augmented Transformer for Speech Recognition. In Interspeech 2020, pages 5036–5040.
  65. Injy Hamed, Nizar Habash, Slim Abdennadher, and Ngoc Thang Vu. 2022. ArzEn-ST: A three-way speech translation corpus for code-switched Egyptian Arabic-English. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 119–130, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. ↗
  66. Injy Hamed, Ngoc Thang Vu, and Slim Abdennadher. 2020. ArzEn: A speech corpus for code-switched Egyptian Arabic-English. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4237–4246, Marseille, France. European Language Resources Association. find
  67. Kenneth Heafield. 2011. KenLM: Faster and smaller language model queries. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 187–197, Edinburgh, Scotland. Association for Computational Linguistics.
  68. Geoffrey Hinton, Li Deng, Dong Yu, George E. Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N. Sainath, and Brian Kingsbury. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6):82–97. ↗
  69. Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. HuBERT: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29:3451–3460. ↗
  70. Musab Iskandar, Mohamed Ebrahim, Adel Alharbi, Khaled Alharbi, and Youssef Mohamed. 2026. AI Elites at NADI 2026 Shared Task: Selecting on Out-of-Domain Accuracy for Cross-Domain Spoken Arabic Dialect Identification. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  71. KAND CA. 2026. Lahgtna huggingface dataset. find
  72. Woohyun Kang, Md Jahangir Alam, and Abderrahim Fathan. 2022. Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7339–7343, Marseille, France. European Language Resources Association. find
  73. Salma Khaled. 2026. CIS-OpenSLU at NADI 2026 Shared Task: ASR-Matched Training and Confidence-Based Rejection for Open-Set Tunisian Arabic Intent Recognition. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  74. Ahmed Khamis and Hesham Ali Ahmed. 2026. LLM-to-Speech: A synthetic data pipeline for training dialectal text-to-speech models. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, page 47–54. Association for Computational Linguistics.
  75. Ondřej Klejch, William Lamb, and Peter Bell. 2025. A Practitioner’s Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic. In Interspeech 2025, pages 728–732. find
  76. Moksh Kopikar and Naman Mandloi. 2026. Amchi-low resource language ASR with crowdsourced post-processing. In Proc. SpeechProsody 2026, pages 924–925. find
  77. Saurabh Kumar, Amartyaveer, and Prasanta Kumar Ghosh. 2025. Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion. In Interspeech 2025, pages 2770– 2774. find
  78. Imen Laouirine, Rami Kammoun, and Fethi Bougares. 2024. TunArTTS: Tunisian Arabic text-to-speech corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16879–16889, Torino, Italia. ELRA and ICCL.
  79. Gaëlle Laperrière, Valentin Pelloin, Antoine Caubrière, Salima Mdhaffar, Nathalie Camelin, Sahar Ghannay, Bassam Jabaian, and Yannick Estève. 2022. The spoken language understanding MEDIA benchmark dataset in the era of deep learning: data updates, training and evaluation tools. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1595–1602, Marseille, France. European Language Resources Association. find
  80. Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, Antoine Thiol, Hugo Riguidel, Salima Mdhaffar, Gaëlle Laperrière, Lucas Maison, Sameer Khurana, and Yannick Estève. 2023. ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 219–226, Toronto, Canada (in-person and online). Association for Computational Linguistics. ↗
  81. Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, and Laurent Besacier. 2024. Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond. In Interspeech 2024, pages 817–821. find
  82. Yooyoung Lee, Craig Greenberg, Lisa Mason, and Elliot Singer. 2022. NIST 2022 language recognition evaluation plan. National Institute of Standards and Technology. find
  83. Chahira Lhioui, Anis Zouaghi, and Mounir Zrigui. 2013. A combined method based on stochastic and linguistic paradigm for the understanding of Arabic spontaneous utterances. In International Conference on Intelligent Text Processing and Computational Linguistics, pages 549–558. Springer. find
  84. Zhaolin Li and Jan Niehues. 2025. In-context Language Learning for Endangered Languages in Speech Recognition. In Interspeech 2025, pages 738–742. find
  85. Mohamed Lichouri, Mourad Abbas, Rachida Djeradi, and Amar Djeradi. 2019. An Arabic multi-domain spoken language understanding system. In Proceedings of the 3rd International Conference on Natural Language and Speech Processing, pages 49–53.
  86. Shervin Malmasi and Marcos Zampieri. 2016. Arabic dialect identification in speech transcripts. In Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3), pages 106–113, Osaka, Japan.
  87. The COLING 2016 Organizing Committee. find
  88. Salima Mdhaffar, Fethi Bougares, Renato de Mori, Salah Zaiem, Mirco Ravanelli, and Yannick Estève. 2024a. TARIC-SLU: A Tunisian benchmark dataset for spoken language understanding. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15606–15616, Torino, Italia. ELRA and ICCL. find
  89. Salima Mdhaffar, Haroun Elleuch, Fethi Bougares, and Yannick Estève. 2024b. Performance analysis of speech encoders for low-resource SLU and ASR in Tunisian dialect. In Proceedings of the Second Arabic Natural Language Processing Conference, pages 130–139, Bangkok, Thailand. Association for Computational Linguistics.
  90. Salima Mdhaffar, Haroun Elleuch, Chaimae Chellaf, Ha Nguyen, and Yannick Estève. 2025. Sense models: an open source solution for multilingual and multimodal semantic-based tasks. In 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1–8. IEEE. ↗
  91. Pouya Mehralian and Hugo Van hamme. 2025. Leveraging geographic metadata for dialect-aware speech recognition. In Interspeech 2025, pages 1153–1157. find
  92. Gabriel Mittag and Sebastian Möller. 2020. Deep Learning Based Assessment of Synthetic Speech Naturalness. In Interspeech 2020, pages 1748–1752. find
  93. Gabriel Mittag, Babak Naderi, Assmaa Chehadi, and Sebastian Möller. 2021. Nisqa: A deep cnn-self-attention model for multidimensional speech quality prediction with crowdsourced datasets. In Interspeech 2021, page 2127–2131. ISCA. find
  94. Hamid Mojarad and Kevin Tang. 2025. Automatic Speech Recognition of African American English: Lexical and Contextual Effects. In Interspeech 2025, pages 3883–3887. ↗
  95. 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, Online. Association for Computational Linguistics. oddadmix. 2024. lahgtna-chatterbox-v1. Hugging Face. Accessed: Aug. 9, 2026. ↗
  96. Omnilingual ASR, Gil Keren, Artyom Kozhevnikov, Yen Meng, Christophe Ropers, Matthew Setzler, Skyler Wang, Ife Adebara, Michael Auli, Can Balioglu, and 1 others. 2025. Omnilingual ASR: Open-source multilingual speech recognition for 1600+ languages. arXiv preprint arXiv:2511.09690. ↗
  97. Abdulaziz Otaif, Hazem Bakhshwain, Abdulhamid Al-doobi, Meshal Alamr, and Abdullah Aldahlawi. 2026. Thakaa at NADI 2026 Shared Task: ROVER Ensembling and Multi-Representation Fusion for Robust Arabic ASR and Dialect Identification. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  98. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics. ↗
  99. Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, and Quoc V. Le. 2019. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition. In Interspeech 2019, pages 2613–2617.
  100. Karol J Piczak. 2015. ESC: Dataset for environmental sound classification. In Proceedings of the 23rd ACM international conference on Multimedia, pages 1015– 1018. find
  101. Maja Popović. 2015. chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics. ↗
  102. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Brussels, Belgium. Association for Computational Linguistics. ↗
  103. Jeena Prakash, Blessingh Kumar, Kadri Hacioglu, Bidisha Sharma, Sindhuja Gopalan, Malolan Chetlur, Shankar Venkatesan, and Andreas Stolcke. 2025. Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM. In Interspeech 2025, pages 579–583. find
  104. 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.
  105. Lawrence R. Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257– 286. ↗
  106. 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. ↗
  107. Dima Rekesh, Nithin Rao Koluguri, Samuel Kriman, Somshubra Majumdar, Vahid Noroozi, He Huang, Oleksii Hrinchuk, Krishna Puvvada, Ankur Kumar, Jagadeesh Balam, and 1 others. 2023. Fast Conformer with linearly scalable attention for efficient speech recognition. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1–8. IEEE. find
  108. Mohamed Sabaa and Amr Sabaa. 2026. Sabaa at NADI 2026 Subtask 1.1: Matching Annotation Conventions for Dialectal Arabic ASR. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  109. Omar Samir, Youssef Waleed, Youssef Tamer, and Amir Mohamed. 2024. Fine-tuning XTTS V2 for Egyptian Arabic. find
  110. Dana Serditova, Kevin Tang, and Jochen Steffens. 2025. Automatic speech recognition biases in Newcastle English: An error analysis. arXiv preprint arXiv:2506.16558. ↗
  111. Tajwaar Shafiq, Hunzalah Hassan Bhatti, Firoj Alam, and Shammur Absar Chowdhury. 2026. Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. ↗
  112. Omar Shoaib, Mohamed Sokar, Mohamed Motawie, Omar AboElFottouh, Ahmed Hassouna, AlAmir Hassan, Nader Essam, and Wael Ali. 2026. Resonate at NADI 2026 Shared Task: Robust Speech Recognition and Dialect Identification under Acoustic and Domain Shift. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  113. Suwon Shon, Ahmed Ali, and James Glass. 2017. MIT-QCRI Arabic dialect identification system for the 2017 multi-genre broadcast challenge. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 374–380. IEEE.
  114. Silero Team. 2024. Silero VAD: pre-trained enterprise-grade voice activity detector (VAD), number detector and language classifier. https://github.com/snakers4/silero-vad. ↗
  115. SILMA AI. 2026. Arabic Text-to-Speech (TTS) models. https://silma.ai/arabic-tts-models. Accessed: Aug. 9, 2026. ↗
  116. Marta Smolarek. 2019. Amazon Polly adds Arabic language support. AWS Machine Learning Blog. Accessed: Aug. 9, 2026. find
  117. David Snyder, Daniel Garcia-Romero, Alan McCree, Gregory Sell, Daniel Povey, and Sanjeev Khudanpur. 2018. Spoken language recognition using x-vectors. In Odyssey, volume 2018, pages 105–111. find
  118. Peter Sullivan, AbdelRahim Elmadany, and Muhammad Abdul-Mageed. 2023. On the robustness of Arabic speech dialect identification. In Interspeech 2023, pages 5326–5330.
  119. Peter Sullivan, AbdelRahim A. Elmadany, Alcides Alcoba Inciarte, and Muhammad Abdul-Mageed. 2026. Arab voices: Mapping standard and dialectal Arabic speech technology. In Findings of the Association for Computational Linguistics: ACL 2026, pages 11843–11878, San Diego, California, United States. Association for Computational Linguistics. ↗
  120. 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, Aisha Alraeesi, Hour Mohamed, Fakhraddin Alwajih, Abdelrahman Mohamed, Abdellah El Mekki, El Moatez Billah Nagoudi, Benelhadj Djelloul Mama Saadia, Hamzah A. Alsayadi, Walid Al-Dhabyani, and 8 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, Miami, Florida, USA. Association for Computational Linguistics.
  121. Bashar Talafha, Hawau Olamide Toyin, Peter Sullivan, AbdelRahim A. Elmadany, Abdurrahman Juma, Amirbek Djanibekov, Chiyu Zhang, Hamad Alshehhi, Hanan Aldarmaki, Mustafa Jarrar, Nizar Habash, and Muhammad Abdul-Mageed. 2025. NADI 2025: The first multidialectal Arabic speech processing shared task. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 720–733, Suzhou, China. Association for Computational Linguistics. ↗
  122. Xu Tan, Tao Qin, Frank Soong, and Tie-Yan Liu. 2021. A survey on neural speech synthesis. Preprint, arXiv:2106.15561. ↗
  123. 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.
  124. Gokhan Tur and Renato De Mori. 2011. Spoken language understanding: Systems for extracting semantic information from speech. John Wiley & Sons. find
  125. 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
  126. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30.
  127. Pengcheng Wang, Sheng Li, and Takahiro Shinozaki. 2025a. RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition. In Workshop on Multilingual Conversational Speech Language Model (MLC-SLM), pages 54–55. ↗
  128. Yingzhi Wang, Anas Alhmoud, and Muhammad Alqurishi. 2025b. Open Universal Arabic ASR Leaderboard. In Interspeech 2025, pages 1168–1172.
  129. Ahmed Wasfy and Nourhan Anber. 2026. KAND CA at NADI 2026 Shared Task: Multi-Stage Fine-Tuning for Spoken Arabic Dialects. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  130. Bajian Xiang, Cheng Wen, Han Zhao, Hao Wang, Haoxu Wang, Jiawei Jin, Jiayan Cui, Jie Chen, Mengxi Nie, Tianyu Zhao, Weiqin Li, Xiang Lv, Xiangang Li, Yang Xiang, and Yang Zhou. 2026. Qwen-Audio-3.0-TTS: Freely controllable and highly robust speech synthesis with multi-stage training paradigm. Preprint, arXiv:2607.23938. ↗
  131. Tianyi Xu, Hongjie Chen, Qing Wang, Lv Hang, Jian Kang, Jie Li, Zhennan Lin, Yongxiang Li, and Lei Xie. 2025. Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis. In Interspeech 2025, pages 584–588. find
  132. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 483–498, Online. Association for Computational Linguistics. ↗
  133. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388. ↗
  134. Hongli Yang, Yizhou Peng, Hao Huang, and Sheng Li. 2025b. Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning. In Interspeech 2025, pages 5203–5207. find
  135. Sarah Yassine and Abdulkadir Shehu Bichi. 2026. Code-Zone Research Group at NADI 2026 Shared Task: Cross-Domain Score Calibration for Spoken Arabic Dialect Identification. In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026), Budapest, Hungary. Association for Computational Linguistics. find
  136. Shengkui Zhao, Zexu Pan, and Bin Ma. 2025. ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment. In Interspeech 2025, pages 2980–2984. find
  137. Yixuan Zhou, Guoyang Zeng, Xin Liu, Xiang Li, Renjie Yu, Jiancheng Gui, Jiaheng Wu, Ziyang Wang, Xudong Shen, Runchuan Ye, and 1 others. 2026. VoxCPM2 technical report. arXiv preprint arXiv:2606.06928. ↗
  138. Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, and Daniel Povey. 2026. OmniVoice: Towards omnilingual zero-shot text-to-speech with diffusion language models. arXiv preprint arXiv:2604.00688. ↗
  139. Jianheng Zhuo, Yifan Yang, Yiwen Shao, Yong Xu, Dong Yu, Kai Yu, and Xie Chen. 2025. VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining. In Interspeech 2025, pages 1163–1167. find
  140. Ömer Tarik Özyilmaz, Matt Coler, and Matias Valdenegro-Toro. 2025. Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning. In Interspeech 2025, pages 1158–1162.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sullivan-2026-nadi-2026-second-multidialectal-arabic/