Elamur Research⌕
☰
home / papers / 2023 / AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

Paper · 2023 · Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli et al.

Summary

Speech recognition systems now reach near-human accuracy on standard English benchmarks. They still perform poorly on African-accented speech, and no public resource existed for clinical ASR on such accents. This gap matters for African clinicians, who face heavy patient loads and could benefit from dictation tools. The authors built AfriSpeech-200, a crowd-sourced corpus of read English speech from speakers across Africa. It covers both general and clinical domains.

To create prompts, they combined sampled Wikitext-103 sentences with text scraped from African news and health websites. They also used a templating approach to insert native African proper nouns into existing text. They benchmarked several pre-trained open-source models and commercial ASR services, analysed where these systems fail, and fine-tuned the strongest open models. The fine-tuned models outperformed both baselines and commercial systems by a wide margin and showed encouraging zero-shot behaviour on very-low-resource accents. The work shows that more diverse training data substantially improves generalisation. It also warns that strong LibriSpeech scores can hide poor robustness to accented speech.

Key points

  • AfriSpeech-200 contains 200.70 hours in 67,577 clips from 2,463 speakers, covering 120 accents from 13 countries. Clips average about 10.7 seconds, and Nigerian accents make up roughly 67% of the data.
  • The dataset is on Hugging Face (tobiolatunji/afrispeech-200) under CC BY-NC-SA 4.0, with a benchmark test set spanning 108 accents. Fine-tuned checkpoints are also public.
  • Fine-tuned models achieved about 49.8% average relative WER improvement over commercial systems (Azure, GCP, AWS).
  • Many pre-trained models are 3–10x worse on AfriSpeech than on LibriSpeech. Multilingual or multi-task models such as Whisper, Conformer and XLSR hold up better.
  • The authors note several limitations:
    • All audio is read speech.
    • North African accents are absent.
    • Accent labels are self-reported.
    • Clinical specialties are incompletely covered.
    • Medical abbreviations are pronounced inconsistently.

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

🎓McGill UniversityMontreal · Canada87 works · 11,027 citations🔬Mila - Quebec Artificial Intelligence InstituteMontreal · Canada54 works · 13,565 citations🎓University of MinnesotaMinneapolis · United States28 works · 2,184 citations🎓Instituto Politécnico NacionalMexico City · Mexico18 works · 4,307 citations🔬Helmholtz Center for Information SecuritySaarbrücken · Germany14 works · 1,172 citations🏢Ford Motor CompanyDearborn · United States2 works · 613 citations🎓University of Colorado Colorado SpringsColorado Springs · United States2 works · 60 citations

 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 1Research subjects and languages the work is about.Speech & spoken language · 480 works

Cite

Cite as Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, Chris Chinenye Emezue, Sahib Singh, Bonaventure F. P. Dossou, Joanne Osuchukwu, Salomey Osei, Atnafu Lambebo Tonja, Naome Etori and Clinton Mbataku. 2023. AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00627

@article{olatunji2023afrispeech,
  title = {{AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR}},
  author = {Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, Chris Chinenye Emezue, Sahib Singh, Bonaventure F. P. Dossou, Joanne Osuchukwu, Salomey Osei, Atnafu Lambebo Tonja, Naome Etori and Clinton Mbataku},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  doi = {10.1162/tacl\_a\_00627},
  url = {https://doi.org/10.1162/tacl_a_00627}
}

References

77 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. World Health Organization. Chronic staff shortfalls stifle Africa’s health systems: WHO study — afro.who.int. https://www.afro.who.int/news/chronic-staff-shortfalls -stifle-africas-health-systems-who-study. [Accessed 15-Oct-2022]. ↗
  2. Mohammed Abdelwahab and Carlos Busso. 2015. Supervised domain adaptation for emotion recognition from speech. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5058–5062. IEEE. https://doi.org/10.1109/ICASSP .2015.7178934 — [doi:10.1109/icassp](https://doi.org/10.1109/icassp) ↗
  3. Tejumade Afonja, Oladimeji Mudele, Iroro Orife, Kenechi Dukor, Lawrence Francis, Duru Goodness, Oluwafemi Azeez, Ademola Malomo, and Clinton Mbataku. 2021. Learning nigerian accent embeddings from speech: Preliminary results based on sautidb-naija corpus. arXiv preprint arXiv:2112.06199. — [arXiv:2112.06199](https://arxiv.org/abs/2112.06199) find
  4. Christoph Ahlgrim, Oliver Maenner, and Manfred W. Baumstark. 2016. Introduction of digital speech recognition in a specialised outpatient department: A case study. BMC Medical Informatics and Decision Making, 16(1):1–8. https://doi.org/10.1186/s12911-016 -0374-4, PubMed: 27756284 — [doi:10.1186/s12911-016](https://doi.org/10.1186/s12911-016) ↗
  5. Adam Ahmat, Sunny C. Okoroafor, Isabel Kazanga, James Avoka Asamani, Jean Jacques Salvador Millogo, Mourtala Mahaman Abdou Illou, Kasonde Mwinga, and Jennifer Nyoni. 2022. The health workforce status in the WHO African region: Findings of a cross-sectional study. BMJ Global Health, 7(Suppl 1):e00831… — [doi:10.1136/bmjgh-2021](https://doi.org/10.1136/bmjgh-2021) find
  6. Richard Anderson, Alex Borucki, Daniel Domingues Da Silva, David Eltis, Paul Lachance, Philip Misevich, and Olatunji Ojo. 2013. Using african names to identify the origins of captives in the transatlantic slave trade: Crowd-sourcing and the registers of liberated Africans, 1808–1862. History in Afri… — [doi:10.1017/hia.2013.3](https://doi.org/10.1017/hia.2013.3) find
  7. Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis M. Tyers, and Gregor Weber. 2019. Common voice: A massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670.
  8. Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis M. Tyers, and Gregor Weber. 2020. Common voice: A massively-multilingual speech corpus. In LREC.
  9. Claire Babirye, Joyce Nakatumba-Nabende, Andrew Katumba, Ronald Ogwang, Jeremy Tusubira Francis, Jonathan Mukiibi, Medadi Ssentanda, Lilian D. Wanzare, and Davis David. 2022. Building text and speech datasets for low resourced languages: A case of languages in east Africa. In 3rd Workshop on African… find
  10. Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Miguel Pino, Alexei Baevski, Alexis Conneau, and Michael Auli. 2022. Xls-r: Self-supervised cross-lingual speech representation learning at scale. In INTERSPEE…
  11. Alexei Baevski, Steffen Schneider, and Michael Auli. 2020a. vq-wav2vec: Self-supervised learning of discrete speech representations. ArXiv, abs/1910.05453. find
  12. Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020b. wav2vec 2.0: A framework for self-supervised learning of speech representations. ArXiv, abs/2006 .11477.
  13. Florence K. Baingana and Eduard R. Bos. 2006. Changing patterns of disease and mortality in sub-saharan Africa: An overview. Disease and Mortality in Sub-Saharan Africa. 2nd edition. find
  14. Suzanne V. Blackley, Jessica Huynh, Liqin Wang, Zfania Korach, and Li Zhou. 2019. Speech recognition for clinical documentation from 1990 to 2018: A systematic review. Journal of the American Medical Informatics Association, 26(4):324–338. https://doi.org/10 .1093/jamia/ocy179, PubMed: 30753666 find
  15. Suzanne V. Blackley, Valerie D. Schubert, Foster R. Goss, Wasim Al Assad, Pamela M. Garabedian, and Li Zhou. 2020. Physician use of speech recognition versus typing in clinical documentation: A controlled observational study. International Journal of Medical Informatics, 141:104178. https://doi.org… — [doi:10.1016/j.ijmedinf.2020.104178](https://doi.org/10.1016/j.ijmedinf.2020.104178) ↗
  16. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — Language Models are Few-Shot Learners
  17. Frederick Bukachi and Neil Pakenham-Walsh. 2007. Information technology for health in developing countries. Chest, 132(5):1624–1630. https://doi.org/10.1378/chest.07 -1760, PubMed: 17998362 — [doi:10.1378/chest.07](https://doi.org/10.1378/chest.07) ↗
  18. Guoguo Chen, Shuzhou Chai, Guan-Bo Wang, Jiayu Du, Weiqiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, and Zhiyong Yan. 2021. Gigaspeech: An e… find
  19. Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, et al. 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. https:… find
  20. Yi-Chen Chen, Zhaojun Yang, Ching feng Yeh, Mahaveer Jain, and Michael L. Seltzer. 2020. Aipnet: Generative adversarial pre-training of accent-invariant networks for end-to-end speech recognition. find
  21. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6979–6983. https://doi.org/10 .1109/ICASSP40776.2020.9053098 find
  22. Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdel rahman Mohamed, and Michael Auli. 2021. Unsupervised cross-lingual representation learning for speech recognition. find
  23. In Interspeech. https://doi.org/10.21437/Interspeech.2021-329 ↗
  24. Nilaksh Das, S. Bodapati, Monica Sunkara, Sundararajan Srinivasan, and Duen Horng Chau. 2021. Best of both worlds: Robust accented speech recognition with adversarial transfer learning. In Interspeech. https://doi.org/10.21437/Interspeech.2021-1888 — [doi:10.21437/interspeech.2021-1888](https://doi.org/10.21437/interspeech.2021-1888) ↗
  25. Ali Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, and Dietrich Klakow. 2022. TOKEN is a MASK: Few-shot named entity recognition with pre-trained language models. In Text, Speech, and Dialogue - 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings, volu… — [doi:10.1007/978-3-031-16270-1](https://doi.org/10.1007/978-3-031-16270-1) find
  26. Febe De Wet, Philippa Louw, and Thomas Niesler. 2007. Human and automatic accent identification of Nguni and Sotho black South African English. South African Journal of Science, 103(3):159–164. find
  27. Rezarta Islamaj Doğan, Robert Leaman, and Zhiyong Lu. 2014. Ncbi disease corpus: A resource for disease name recognition and concept normalization. Journal of Biomedical Informatics, 47:1–10. https://doi.org/10.1016/j.jbi.2013.12.006, PubMed: 24393765 ↗
  28. Bonaventure F. P. Dossou and Chris C. Emezue. 2021. Okwugb\\’e: End-to-end speech recognition for Fon and Igbo. arXiv preprint arXiv: 2103.07762. — [arXiv:2103.07762](https://arxiv.org/abs/2103.07762) find
  29. Moussa Doumbouya, Lisa Einstein, and Chris Piech. 2021. Using radio archives for low-resource speech recognition: Towards an intelligent virtual assistant for illiterate users. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14757–14765. https://doi.org /10.1609/aa… — [doi:10.1609/aaai.v35i17.17733](https://doi.org/10.1609/aaai.v35i17.17733) ↗
  30. David Eberhard, Gary Simons, and Chuck Fennig. 2019. Ethnologue: Languages of the World, 22nd Edition. find
  31. Naome Etori, Ebasa Temesgen, and Maria Gini. 2023. What we know so far: Artificial intelligence in African healthcare. arXiv preprint arXiv:2305.18302. — [arXiv:2305.18302](https://arxiv.org/abs/2305.18302) find
  32. Foster R. Goss, Suzanne V. Blackley, Carlos A. Ortega, Leigh T. Kowalski, Adam B. Landman, Chen-Tan Lin, Marie Meteer, Samantha Bakes, Stephen C. Gradwohl, David W. Bates, and Li Zhou. 2019. A clinician survey of using speech recognition for clinical documentation in the electronic health record. In… — [doi:10.1016/j.ijmedinf.2019.07.017](https://doi.org/10.1016/j.ijmedinf.2019.07.017) find
  33. Ama de Graft Aikins, Nigel Unwin, Charles Agyemang, Pascale Allotey, Catherine Campbell, and Daniel Arhinful. 2010. Tackling Africa’s chronic disease burden: From the local to the global. Globalization and Health, 6(1):1–7. https://doi.org/10.1186/1744-8603-6-5, PubMed: 20403167 ↗
  34. Jonatas Grosman. 2021. Fine-tuned XLSR-53 large model for speech recognition in English. https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, and Ruoming Pa… ↗
  35. Alexander Gutkin, Isin Demirsahin, Oddur Kjartansson, Clara E. Rivera, and Kólá Túbòsún. 2020. Developing an open-source corpus of Yoruba speech. https://doi.org/10.21437/Interspeech.2020-1096 — [doi:10.21437/interspeech.2020-1096](https://doi.org/10.21437/interspeech.2020-1096) ↗
  36. Muhammad Ahmed Hassan, Asim Rehmat, Muhammad Usman Ghani Khan, Muhammad Haroon Yousaf, and Muhammad Fazal Ijaz. 2022. Improvement in automatic speech recognition of south asian accent using transfer learning of deepspeech2. Mathematical Problems in Engineering, 2022. https://doi .org/10.1155/2022/68… — [doi:10.1155/2022/6825555](https://doi.org/10.1155/2022/6825555) find
  37. Bernd Heine and Derek Nurse. 2000. African Languages: An Introduction. Cambridge University Press. find
  38. François Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia Tomashenko, and Yannick Esteve. 2018. Ted-lium 3: Twice as much data and corpus repartition for experiments on speaker adaptation. In International Conference on Speech and Computer, pages 198–208. Springer. https://doi.org/10.1007/978 -3-3… — [doi:10.1007/978](https://doi.org/10.1007/978) ↗
  39. 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. https:…
  40. Sharon Ibejih, Wuraola Fisayo Oyewusi, Olubayo Adekanmbi, and Opeyemi Osakuade. 2022. EDUSTT: In-domain speech recognition for Nigerian accented educational contents in English. In 3rd Workshop on African Natural Language Processing. find
  41. Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman, Kaushal Santosh Bhogale, Gowtham Ramesh, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh M. Khapra. 2022. Towards building asr systems for the next billion users. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10813… find
  42. Herman Kamper and Thomas Niesler. 2011. Multi-accent speech recognition of Afrikaans, black and white varieties of South African English. In Twelfth Annual Conference of the International Speech Communication Association. https://doi.org/10.21437/Interspeech.2011-798 ↗
  43. Yohannes Kinfu, Mario R. Dal Poz, Hugo Mercer, and David B. Evans. 2009. The health worker shortage in Africa: Are enough physicians and nurses being trained? https://doi.org/10 .2471/BLT.08.051599, PubMed: 19377719 find
  44. Allison Koenecke, Andrew Nam, Emily Lake, Joe Nudell, Minnie Quartey, Zion Mengesha, Connor Toups, John R. Rickford, Dan Jurafsky, and Sharad Goel. 2020. Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences, 117(14):7684–7689. https://doi.org/10 .1073/p… find
  45. Jialu Li, Vimal Manohar, Pooja Chitkara, Andros Tjandra, Michael Picheny, Frank Zhang, Xiaohui Zhang, and Yatharth Saraf. 2021. Accent-robust automatic speech recognition using supervised and unsupervised wav2vec embeddings. arXiv preprint arXiv:2110.03520. — [arXiv:2110.03520](https://arxiv.org/abs/2110.03520) find
  46. Abdulaziz Y. Lodhi. 1993. The language situation in africa today. Nordic Journal of African Studies, 2(1):11–11. find
  47. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. find
  48. Tarisai Kudakwashe Manyati and Morgen Mutsau. 2021. A systematic review of the factors that hinder the scale up of mobile health technologies in antenatal care programmes in sub-saharan Africa. African Journal of Science, Technology, Innovation and Development, 13(1):125–131. https://doi.org /10.108… — [doi:10.1080/20421338.2020.1765479](https://doi.org/10.1080/20421338.2020.1765479) ↗
  49. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. https://doi.org/10.48550/arXiv.1609.07843 ↗
  50. Saraladevi Naicker, John B. Eastwood, Jacob Plange-Rhule, and Roger C. Tutt. 2010. Shortage of healthcare workers in sub-saharan Africa: A nephrological perspective. Clinical Nephrology, 74:S129–33. https://doi.org/10 .5414/CNP74S129, PubMed: 20979978 find
  51. Saraladevi Naicker, Jacob Plange-Rhule, Roger C. Tutt, and John B. Eastwood. 2009. Shortage of healthcare workers in developing countries– Africa. Ethnicity & Disease, 19(1):60. PubMed: 19484878 find
  52. Oathokwa Nkomazana, Robert Mash, Sheila Shaibu, and Nthabiseng Phaladze. 2015. Stakeholders’ perceptions on shortage of healthcare workers in primary healthcare in Botswana: Focus group discussions. PloS One, 10(8):e0135846. https://doi.org/10.1371/journal.pone.0135846, PubMed: 26284617 ↗
  53. Perez Ogayo, Graham Neubig, and Alan W. Black. 2022. Building African voices. arXiv preprint arXiv:2207.00688. https://doi.org/10 .21437/Interspeech.2022-152 find
  54. Hilary I. Okagbue, Abiodun A. Opanuga, Muminu O. Adamu, Paulinus O. Ugwoke, Emmanuela C. M. Obasi, and Grace A. Eze. 2017. Personal name in Igbo culture: A dataset on randomly selected personal names and their statistical analysis. Data in Brief, 15:72–80. https://doi.org/10.1016/j.dib.2017 .08.045,… — [doi:10.1016/j.dib.2017](https://doi.org/10.1016/j.dib.2017) ↗
  55. Kayode Olaleye, Dan Oneaţă, and Herman Kamper. 2022. Yfacc: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding. ArXiv, abs/2210 .04600. find
  56. Obinna O. Oleribe, Jenny Momoh, Benjamin S. C. Uzochukwu, Francisco Mbofana, Akin Adebiyi, Thomas Barbera, Roger Williams, and Simon D. Taylor-Robinson. 2019. Identifying key challenges facing healthcare systems in Africa and potential solutions. International Journal of General Medicine, 12:395. ht… — [doi:10.2147/ijgm.s223882](https://doi.org/10.2147/ijgm.s223882) find
  57. 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. https://doi.org/10.1109/ICASSP.2015.7178964 — [doi:10.1109/icassp.2015.7178964](https://doi.org/10.1109/icassp.2015.7178964) ↗
  58. Komal Pawar and Urmila Shrawankar. 2016. Question systematization using templates. In 3rd International Conference on Computing for Sustainable Global Development. find
  59. Archiki Prasad and Preethi Jyothi. 2020. How accents confound: Probing for accent information in end-to-end speech recognition systems. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3739–3753, Online. Association for Computational Linguistics. http… find
  60. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356.
  61. Mirco Ravanelli, Titouan Parcollet, Peter Plantinga, Aku Rouhe, Samuele Cornell, Loren Lugosch, Cem Subakan, Nauman Dawalatabad, Abdelwahab Heba, Jianyuan Zhong, Ju-Chieh Chou, Sung-Lin Yeh, Szu-Wei Fu, Chien-Feng Liao, Elena Rastorgueva, François Grondin, William Aris, Hwidong Na, Yan Gao, Renato… — [arXiv:2106.04624](https://arxiv.org/abs/2106.04624) find
  62. Ramon Sanabria, Nikolay Bogoychev, Nina Markl, Andrea Carmantini, Ondrej Klejch, and Peter Bell. 2023. The Edinburgh International Accents of English corpus: Towards the democratization of English asr. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICAS…
  63. Steffen Schneider, Alexei Baevski, Ronan Collobert, and Michael Auli. 2019. wav2vec: Unsupervised pre-training for speech recognition. In Proceedings of Interspeech 2019, pages 3465–3469. https://doi.org/10 .21437/Interspeech.2019-1873 find
  64. Kathleen Siminyu, Godson Kalipe, Davor Orlic, Jade Abbott, Vukosi Marivate, Sackey Freshia, Prateek Sibal, Bhanu Neupane, David I. Adelani, Amelia Taylor, Jamiil Toure ALI, Kevin Degila, Momboladji Balogoun, Thierno Ibrahima DIOP, Davis David, Chayma Fourati, Hatem Haddad, and Malek Naski. 2021. Ai4… — [arXiv:2104.02516](https://arxiv.org/abs/2104.02516) find
  65. Workshop (SLT), pages 652–658. https://doi.org/10.1109/SLT48900.2021.9383459 — [doi:10.1109/slt48900.2021.9383459](https://doi.org/10.1109/slt48900.2021.9383459) ↗
  66. Markus Vogel, Wolfgang Kaisers, Ralf Wassmuth, and Ertan Mayatepek. 2015. Analysis of documentation speed using web-based medical speech recognition technology: Randomized controlled trial. Journal of Medical Internet Research, 17(11):e5072. https://doi.org/10.2196/jmir.5072, PubMed: 26531850 — [doi:10.2196/jmir.5072](https://doi.org/10.2196/jmir.5072) ↗
  67. David L. Wheeler, Tanya Barrett, Dennis A. Benson, Stephen H. Bryant, Kathi Canese, Vyacheslav Chetvernin, Deanna M. Church, Michael DiCuccio, Ron Edgar, Scott Federhen, et al. 2007. Database resources of the national center for biotechnology information. Nucleic Acids Research, 36(suppl 1):D13–D21.… — [doi:10.1093/nar/gkm1000](https://doi.org/10.1093/nar/gkm1000) find
  68. Wikipedia contributors. 2023a. Demographics of africa — Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index.php? title=Demographics of Africa&oldid =1132870977. [Online; accessed 20-January -2023]. ↗
  69. Sining Sun, Ching feng Yeh, Mei-Yuh Hwang, Mari Ostendorf, and Lei Xie. 2018. Domain adversarial training for accented speech recognition. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4854–4858. https://doi.org/10.1109/ICASSP.2018.8462663 — [doi:10.1109/icassp.2018.8462663](https://doi.org/10.1109/icassp.2018.8462663) ↗
  70. Wikipedia contributors. 2023b. Languages of africa — Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index .php?title=Languages of Africa&oldid =1133594141. [Online; accessed 20-January -2023]. ↗
  71. Sining Sun, Binbin Zhang, Lei Xie, and Yanning Zhang. 2017. An unsupervised deep domain adaptation approach for robust speech recognition. Neurocomputing, 257:79–87. https://doi.org/10.1016/j.neucom.2016.11 .063 — [doi:10.1016/j.neucom.2016.11](https://doi.org/10.1016/j.neucom.2016.11) ↗
  72. Wikipedia contributors. 2023c. List of cities in africa by population — Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index.php?title=List of cities in Africa by population&oldid=1146587606. [Online; accessed 31-March-2023]. ↗
  73. Monica Sunkara, Srikanth Ronanki, Kalpit Dixit, Sravan Bodapati, and Katrin Kirchhoff. 2020. Robust prediction of punctuation and truecasing for medical asr. In ACL 2020 Workshop on NLP for Medical Conversations. https://doi.org/10.18653/v1/2020.nlpmc-1.8 ↗
  74. Aditya Yadavalli, Ganesh S. Mirishkar, and Anil Kumar Vuppala. 2022. Multi-task end-to-end model for telugu dialect and speech recognition. In Interspeech. https://doi.org/10 .21437/Interspeech.2022-10739 find
  75. Jörgen Valk and Tanel Alumäe. 2021. Voxlingua-107: A dataset for spoken language recognition. 2021 IEEE Spoken Language Technology Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, and Jianyong Wang. 2022. find
  76. Prompt tuning for discriminative pre-trained language models. arXiv preprint arXiv:2205 .11166. https://doi.org/10.18653/v1/2022.findings-acl.273 ↗
  77. Yuanyuan Zhang, Yixuan Zhang, Bence Halpern, Tanvina Patel, and Odette Scharenborg. 2022. Mitigating bias against non-native accents. In Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech 2022, pages 3168–3172. https://doi.org/10.21437/Interspeech… — [doi:10.21437/interspeech](https://doi.org/10.21437/interspeech) ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/olatunji-2023-afrispeech-200-pan-african-accented/