Elamur Research⌕
☰
home / papers / 2025 / Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond

Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond

Paper · 2025 · Mardhiyah Sanni, Tassallah Abdullahi, Devendra Deepak Kayande et al.

Summary

Speech systems are now common in clinics and call centers, but little is known about how they handle African-accented English in long, spontaneous dialogue. The authors build Afrispeech-Dialog, a benchmark of 50 simulated two-speaker conversations, roughly 7 hours in total. Some conversations are doctor–patient consultations and others are general-topic chats. Speakers from Nigeria, Kenya and South Africa were recorded on the Intron Platform. Professional annotators then transcribed each conversation by hand, marking speaker turns and timestamps.

On this data the authors benchmark state-of-the-art speaker diarization and ASR systems. Compared with native-accent speech, performance drops by more than 10%. They also ask several LLMs to summarize the medical conversations from either human or machine transcripts, and score the summaries with BERTScore, an LLM judge and blind clinician ratings. ASR errors leave embedding similarity almost unchanged but noticeably lower the fact-level judge scores. This means that noisy transcripts can quietly drop clinically important information. The resource fills a gap for conversational AI in the Global South.

Key points

  • The dataset covers 11 accents, including Hausa, Yoruba, Igbo, Swahili and Sesotho. Table 1 lists 20 medical and 29 general conversations, stored as mono 16-bit 48 kHz wav files.
  • Medical dialogues follow the OSCE format. Clinicians wrote "patient cards" with African-context conditions such as malaria, and these were hidden from the doctor actors. General dialogues used topic cards, each with a description and two prompts.
  • Diarization and ASR models lose more than 10% performance on African-accented speech compared with native accents.
  • The LLM-as-judge scores correlated with human expert ratings at Pearson 0.816.
  • Summary quality on ASR transcripts versus human transcripts:
    • LLM-Eval scores were 2–5 points lower on ASR transcripts.
    • BERTScore showed no significant difference.
    • Claude-3-Sonnet ranked highest on human transcripts and Gemma-2 on ASR transcripts.
    • In blind ratings, experts preferred the leading LLM summaries to the human reference summaries.

Interesting ideas

  • I1. Giving one participant a hidden fact card, as with OSCE patient cards, yields natural question-driven dialogue while keeping a known ground truth to check against.
  • I2. Running the same downstream task on clean and on noisy input isolates error propagation, and a surface-similarity metric can miss that loss entirely while a fact-level check reveals it.
  • I3. The human rubric scores positive findings and negative findings (absent symptoms) as separate criteria, recognizing that negated facts are easy to drop.
  • I4. The authors checked the LLM judge against blind expert ratings before trusting it, and they mixed human reference summaries into the blind pool.

For Mova

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

  • I1 (learn): Self-play could hand one agent a hidden "world card" and let the other agent ask questions. The facts it recovers can then be scored exactly against the card.
  • I2 (learn): Evaluate frames and answers on both gold UD trees and gparse output with fact-level scoring. This shows how much parser error actually costs downstream, rather than relying on tree-level LAS alone.
  • I3 (frames): Frame extraction could tag polarity explicitly. A separate negative-fact recall test would catch cases where "no cough" collapses into "cough".
  • I4 (learn): LLM teacher tiers could be calibrated against a small human-rated set. Including gold items blind, as a control, would show whether the "reference" is really the ceiling.

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

🎓Johns Hopkins UniversityBaltimore · United States248 works · 106,397 citations🎓Georgia Institute of TechnologyAtlanta · United States152 works · 27,763 citations🎓Brown UniversityProvidence · United States80 works · 26,036 citations🎓University of North Carolina at Chapel HillChapel Hill · United States74 works · 23,278 citations🎓University of MinnesotaMinneapolis · United States29 works · 2,184 citations🎓University of FloridaGainesville · United States36 works · 364 citations🎓University of GlasgowGlasgow · United Kingdom14 works · 746 citations🎓Indian Institute of Information Technology AllahabadPrayagraj · India2 works · 11 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 3Research subjects and languages the work is about.English · 2,379 worksEvaluation & benchmarks · 1,341 worksDialogue systems · 654 works

Cite

Cite as Mardhiyah Sanni, Tassallah Abdullahi, Devendra Deepak Kayande, Emmanuel Ayodele, Naome A Etori, Michael Samwel Mollel, Moshood O. Yekini, Chibuzor Okocha, Lukman Enegi Ismaila, Folafunmi Omofoye, Boluwatife A. Adewale and Tobi Olatunji. 2025. Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.naacl-long.426

@inproceedings{sanni2025afrispeech,
  title = {{Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond}},
  author = {Mardhiyah Sanni, Tassallah Abdullahi, Devendra Deepak Kayande, Emmanuel Ayodele, Naome A Etori, Michael Samwel Mollel, Moshood O. Yekini, Chibuzor Okocha, Lukman Enegi Ismaila, Folafunmi Omofoye, Boluwatife A. Adewale and Tobi Olatunji},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.426},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.426}
}

References

65 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Asma Ben Abacha, Wen-wai Yim, Yadan Fan, and Thomas Lin. 2023. An empirical study of clinical note generation from doctor-patient encounters. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2291–2302. find
  2. Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al. 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219. ↗
  3. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774. ↗
  4. David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, Shruti Rijhwani, Michael Beukman, Chester Palen-Michel, Constantine Lignos, Jesujoba O Alabi, Shamsuddeen H Muhammad, Peter Nabende, et al. 2022. Masakhaner 2.0: Africa-centric transfer learning for named entity recognition. arXiv preprint arXiv:2210.12391. ↗
  5. Tejumade Afonja, Tobi Olatunji, Sewade Ogun, Naome A Etori, Abraham Owodunni, and Moshood Yekini. 2024. Performant asr models for medical entities in accented speech. arXiv preprint arXiv:2406.12387. ↗
  6. Alëna Aksënova, Zhehuai Chen, Chung-Cheng Chiu, Daan van Esch, Pavel Golik, Wei Han, Levi King, Bhuvana Ramabhadran, Andrew Rosenberg, Suzan Schwartz, et al. 2022. Accented speech recognition: Benchmarking, pre-training, and diverse data. arXiv preprint arXiv:2205.08014. ↗
  7. Rie Kubota Ando and Tong Zhang. 2005. A framework for learning predictive structures from multiple tasks and unlabeled data. Journal of Machine Learning Research, 6:1817–1853. ↗
  8. Galen Andrew and Jianfeng Gao. 2007. Scalable training of L1-regularized log-linear models. In Proceedings of the 24th International Conference on Machine Learning, pages 33–40. find
  9. Anthropic. 2023. The claude 3 model family: Opus, sonnet, haiku. Accessed: 2024-10-15. find
  10. Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449–12460.
  11. Yohannes Baye, Tesfaye Demeke, Nigusie Birhan, Agu-masie Semahegn, and Simon Birhanu. 2020. Nurses’ work-related stress and associated factors in governmental hospitals in harar, eastern ethiopia: A cross-sectional study. PloS one, 15(8):e0236782. ↗
  12. Nishchal Bhandari, Danny Chen, Miguel Ángel del Río Fernández, Natalie Delworth, Jennifer Drexler Fox, Migüel Jetté, Quinten McNamara, Corey Miller, Ondřej Novotný, Ján Profant, Nan Qin, Martin Ratajczak, and Jean-Philippe Robichaud. 2024. Reverb: Open-source asr and diarization from rev. Preprint, arXiv:2410.03930. ↗
  13. Jasmin Bharadiya. 2023. A comprehensive survey of deep learning techniques natural language processing. European Journal of Technology, 7(1):58–66. ↗
  14. Anjanava Biswas and Wrick Talukdar. 2024. Intelligent clinical documentation: Harnessing generative ai for patient-centric clinical note generation. arXiv preprint arXiv:2405.18346. ↗
  15. Hervé Bredin, Ruiqing Yin, Juan Manuel Coria, Gregory Gelly, Pavel Korshunov, Marvin Lavechin, Diego Fustes, Hadrien Titeux, Wassim Bouaziz, and Marie-Philippe Gill. 2020. Pyannote. audio: neural building blocks for speaker diarization. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7124–7128. IEEE. find
  16. Hervé Bredin. 2023. pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe. In Proc. INTERSPEECH 2023. find
  17. Jean Carletta, Simone Ashby, Sebastien Bourban, Mike Flynn, Mael Guillemot, Thomas Hain, Jaroslav Kadlec, Vasilis Karaiskos, Wessel Kraaij, Melissa Kronenthal, et al. 2005. The ami meeting corpus: A pre-announcement. In International workshop on machine learning for multimodal interaction, pages 28–39. Springer. find
  18. Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Xiangzhan Yu, and Furu Wei. 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. ↗
  19. Clément Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, and Marco AF Pimentel. 2024. Med42-v2: A suite of clinical llms. ↗
  20. Victoria YH Chua, Hexin Liu, Leibny Paola Garcia Perera, Fei Ting Woon, Jinyi Wong, Xiangyu Zhang, Sanjeev Khudanpur, Andy WH Khong, Justin Dauwels, and Suzy J Styles. 2023. Merlion ccs challenge: A english-mandarin code-switching child-directed speech corpus for language identification and diarization. arXiv preprint arXiv:2305.18881. ↗
  21. Miguel Del Rio, Peter Ha, Quinten McNamara, Corey Miller, and Shipra Chandra. 2022. Earnings-22: A practical benchmark for accents in the wild. arXiv preprint arXiv:2203.15591. ↗
  22. Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck. 2020. Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv preprint arXiv:2005.07143. ↗
  23. George R Doddington, Mark A Przybocki, Alvin F Martin, and Douglas A Reynolds. 2000. The nist speaker recognition evaluation–overview, methodology, systems, results, perspective. Speech communication, 31(2-3):225–254. ↗
  24. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783. ↗
  25. Seppo Enarvi, Marilisa Amoia, Miguel Del-Agua Teba, Brian Delaney, Frank Diehl, Stefan Hahn, Kristina Harris, Liam McGrath, Yue Pan, Joel Pinto, et al. 2020. Generating medical reports from patient-doctor conversations using sequence-to-sequence models. In Proceedings of the first workshop on natural language processing for medical conversations, pages 22–30. find
  26. and Shadab Khan. 2024. Medic: Towards a comprehensive framework for evaluating llms in clinical applications. arXiv preprint arXiv:2409.07314. ↗
  27. Nithin Rao Koluguri, Taejin Park, and Boris Ginsburg. 2022. Titanet: Neural model for speaker representation with 1d depth-wise separable convolutions and global context. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8102–8106. ↗
  28. Alex Papadopoulos Korfiatis, Francesco Moramarco, Radmila Sarac, and Aleksandar Savkov. 2022. Primock57: A dataset of primary care mock consultations. arXiv preprint arXiv:2204.00333. ↗
  29. Naome Etori, Ebasa Temesgen, and Maria Gini. 2023. What we know so far: Artificial intelligence in african healthcare. arXiv preprint arXiv:2305.18302. ↗
  30. Harold W Kuhn. 1955. The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1-2):83–97. ↗
  31. Faiha Fareez, Tishya Parikh, Christopher Wavell, Saba Shahab, Meghan Chevalier, Scott Good, Isabella De Blasi, Rafik Rhouma, Christopher McMahon, Jean-Paul Lam, et al. 2022. A dataset of simulated patient-physician medical interviews with a focus on respiratory cases. Scientific Data, 9(1):313. find
  32. Federico Landini, Ján Profant, Mireia Diez, and Lukáš Burget. 2022. Bayesian hmm clustering of x-vector sequences (vbx) in speaker diarization: Theory, implementation and analysis on standard tasks. Computer Speech Language, 71:101254. ↗
  33. J Luke Galloway, Dominique Munroe, Pamela D Vohra-Khullar, Christopher Holland, Mary A Solis, Miranda A Moore, and Reema H Dbouk. 2024. Impact of an artificial intelligence-based solution on clinicians’ clinical documentation experience: Initial findings using ambient listening technology. Journal of General Internal Medicine, pages 1–3. ↗
  34. Sanchit Gandhi, Patrick von Platen, and Alexander M Rush. 2023. Distil-whisper: Robust knowledge distillation via large-scale pseudo labelling. arXiv preprint arXiv:2311.00430. ↗
  35. Martucci Giuseppe, Mauro Cettolo, Matteo Negri, and Marco Turchi. 2021. Lexical modeling of asr errors for robust speech translation. In Proceedings of Interspeech 2021, pages 2282–2286. find
  36. Michael Hanna and Ondřej Bojar. 2021. A fine-grained analysis of bertscore. In Proceedings of the Sixth Conference on Machine Translation, pages 507–517. ↗
  37. Eric Harper, Somshubra Majumdar, Oleksii Kuchaiev, Li Jason, Yang Zhang, E Bakhturina, V Noroozi, S Subramanian, K Nithin, H Jocelyn, et al. 2019. Nemo: A toolkit for conversational ai and large language models. Computer software], URL: https://github.com/NVIDIA/NeMo. ↗
  38. Arthur Hinsvark, Natalie Delworth, Miguel Del Rio, Quinten McNamara, Joshua Dong, Ryan Westerman, Michelle Huang, Joseph Palakapilly, Jennifer Drexler, Ilya Pirkin, et al. 2021. Accented speech recognition: A survey. arXiv preprint arXiv:2104.10747. ↗
  39. Praveen K Kanithi, Clément Christophe, Marco AF Pimentel, Tathagata Raha, Nada Saadi, Hamza Javed, Svetlana Maslenkova, Nasir Hayat, Ronnie Rajan, Khai Le-Duc, Khai-Nguyen Nguyen, Long Vo-Dang, and Truong-Son Hy. 2024. Real-time speech summarization for medical conversations. arXiv preprint arXiv:2406.15888. ↗
  40. Yixin Liu, Alexander R Fabbri, Jiawen Chen, Yilun Zhao, Simeng Han, Shafiq Joty, Pengfei Liu, Dragomir Radev, Chien-Sheng Wu, and Arman Cohan. 2023. Benchmarking generation and evaluation capabilities of large language models for instruction controllable summarization. arXiv preprint arXiv:2311.09184. ↗
  41. Anirudh Mani, Shruti Palaskar, and Sandeep Konam. 2020. Towards understanding asr error correction for medical conversations. In Proceedings of the first workshop on natural language processing for medical conversations, pages 7–11. find
  42. George Michalopoulos, Kyle Williams, Gagandeep Singh, and Thomas Lin. 2022. Medicalsum: A guided clinical abstractive summarization model for generating medical reports from patient-doctor conversations. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4741– 4749. find
  43. Hoang-Thi Nguyen-Vo, Huy Nguycn-Gia, Hoan-Duy Nguyen-Tran, Hoang Pham-Minh, Hung Vo-Thanh, and Hao Do-Due. 2022. Marblenet: A deep neural network solution for vietnamese voice activity detection. In 2022 9th NAFOSTED Conference on Information and Computer Science (NICS), pages 154–158. find
  44. Sewade Ogun, Abraham T Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji, Tejumade Afonja, Kayode Olaleye, Naome A Etori, and Tosin Adewumi. 2024. 1000 african voices: Advancing inclusive multi-speaker multi-accent speech synthesis. arXiv preprint arXiv:2406.11727. ↗
  45. Tobi Olatunji, Tejumade Afonja, Bonaventure FP Dossou, Atnafu Lambebo Tonja, Chris Chinenye Emezue, Amina Mardiyyah Rufai, and Sahib Singh. 2023a. Afrinames: Most asr models" butcher" african names. arXiv preprint arXiv:2306.00253. ↗
  46. Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, Chris Chinenye Emezue, Sahib Singh, Bonaventure FP Dossou, Joanne Osuchukwu, Salomey Osei, Atnafu Lambebo Tonja, Naome Etori, et al. 2023b. Afrispeech-200: Pan-african accented speech dataset for clinical and general domain asr. Transactions of the Association for Computational Linguistics, 11:1669–1685. ↗
  47. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: an asr corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5206–5210. IEEE. find
  48. Hannaneh B Pasandi and Haniyeh B Pasandi. 2022. Evaluation of asr systems for conversational speech: A linguistic perspective. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems, pages 962–965. find
  49. Piotr P˛ezik, Gosia Krawentek, Sylwia Karasińska, Paweł Wilk, Paulina Rybińska, Anna Cichosz, Angelika Peljak-Łapińska, Mikołaj Deckert, and Michał Adamczyk. 2022. Diabiz–an annotated corpus of polish call center dialogs. In Proceedings of the thirteenth language resources and evaluation conference, pages 723–726. find
  50. Mirosław Płaza, Łukasz Pawlik, and Stanisław Deniziak. 2021. Call transcription methodology for contact center systems. IEEE Access, 9:110975– 110988. ↗
  51. Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, et al. 2024. Scaling speech technology to 1,000+ languages. Journal of Machine Learning Research, 25(97):1–52. ↗
  52. Krishna C Puvvada, Piotr Żelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, et al. 2024. Less is more: Accurate speech recognition & translation without web-scale data. arXiv preprint arXiv:2406.19674. ↗
  53. 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. ↗
  54. Mohammad Sadegh Rasooli and Joel R. Tetreault. 2015. Yara parser: A fast and accurate dependency parser. Computing Research Repository, arXiv:1503.06733. Version 2. ↗
  55. Mirco Ravanelli and Yoshua Bengio. 2018. Speaker recognition from raw waveform with sincnet. 2018 IEEE Spoken Language Technology Workshop (SLT), pages 1021–1028. find
  56. Neville Ryant, Kenneth Church, Christopher Cieri, Alejandrina Cristia, Jun Du, Sriram Ganapathy, and Mark Liberman. 2019. The second dihard diarization challenge: Dataset, task, and baselines. pages 978–982. find
  57. Oleg Serikov, Ekaterina Voloshina, Anna Postnikova, Saliha Muradoğlu, Éric Le Ferrand, Elena Klyachko, Ekaterina Vylomova, Tatiana Shavrina, and Francis Tyers. 2024. Proceedings of the 3rd workshop on nlp applications to field linguistics (field matters 2024). In Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024). find
  58. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. 2023. Large language models encode clinical knowledge. Nature, 620(7972):172–180. ↗
  59. Gabriel Skantze. 2021. Turn-taking in conversational systems and human-robot interaction: a review. Computer Speech & Language, 67:101178. ↗
  60. Georgios P Spithourakis, Ivan Vulić, Michał Lis, Iñigo Casanueva, and Paweł Budzianowski. 2022. Evi: Multilingual spoken dialogue tasks and dataset for knowledge-based enrolment, verification, and identification. arXiv preprint arXiv:2204.13496. ↗
  61. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. 2024. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118. ↗
  62. Mohamad-Hani Temsah, Amr Jamal, Khalid Alhasan, Abdulkarim A Temsah, and Khalid H Malki. 2024. Openai o1-preview vs. chatgpt in healthcare: A new frontier in medical ai reasoning. Cureus, 16(10). ↗
  63. Atnafu Lambebo Tonja, Israel Abebe Azime, Tadesse Destaw Belay, Mesay Gemeda Yigezu, Moges Ahmed Mehamed, Abinew Ali Ayele, Ebrahim Chekol Jibril, Michael Melese Woldeyohannis, Olga Kolesnikova, Philipp Slusallek, et al. 2024. Ethiollm: Multilingual large language models for ethiopian languages with task evaluation. arXiv preprint arXiv:2403.13737. ↗
  64. Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, and Emmanuel Dupoux. 2021. VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. 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 993–1003, Online. Association for Computational Linguistics. ↗
  65. Lucy Lu Wang, Yulia Otmakhova, Jay DeYoung, Thinh Hung Truong, Bailey E Kuehl, Erin Bransom, and Byron C Wallace. 2023. Automated metrics for medical multi-document summarization disagree with human evaluations. arXiv preprint arXiv:2305.13693. A ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sanni-2025-afrispeech-dialog-benchmark-dataset-spontaneous/