BembaSpeech: A Speech Recognition Corpus for the Bemba Language
Not on the map. Why?
Abstract (arXiv)
We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The corpus and models are publicly released at https://github.com/csikasote/BembaSpeech.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 6 of its 50 references that are in the map. First posted on arXiv 9 Feb 2021.
Builds on
6 of 50 references.
References · 6
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
- 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
- 2018The PyTorch-Kaldi Speech Recognition Toolkitcited by 38
- 2019Benchmarking Neural Machine Translation for Southern African Languagescited by 9
Built on by
Citing papers per year: 2022: 2; 2023: 2; 2024: 4; 2025: 4; 2026: 2.
14 papers.
Sort:
- 2023Zambezi Voice: A Multilingual Speech Corpus for Zambian Languagescited by 18
- 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
- 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialectscited by 11
- 2023BIG-C: a Multimodal Multi-Purpose Dataset for Bembacited by 9
- 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Contextcited by 8
- 2022Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluationcited by 6
- 2022Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learningcited by 5
- 2024Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guidelinecited by 4
- 2025Voice of a Continent: Mapping Africa's Speech Technology Frontiercited by 4
- 2025Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languagescited by 3
- 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Reviewcited by 2
- 2026Sylber 2.0: A Universal Syllable Embeddingcited by 2
2 more
- 2026AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages9 Apr 2026
- 2026Sylber 2.0: A Universal Syllable Embedding29 Jan 2026
- 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review1 Oct 2025
- 2025Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages20 Jun 2025
- 2025Voice of a Continent: Mapping Africa's Speech Technology Frontier24 May 2025
- 2025Bemba Speech Translation: Exploring a Low-Resource African Language5 May 2025
- 2024The Zeno's Paradox of `Low-Resource' Languages28 Oct 2024
- 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialects27 Jun 2024
- 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context2 Apr 2024
- 2024Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline26 Jan 2024
- 2023Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages7 Jun 2023
- 2023BIG-C: a Multimodal Multi-Purpose Dataset for Bemba26 May 2023
- 2023Zambezi Voice: A Multilingual Speech Corpus for Zambian Languagescited by 18
- 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
- 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialectscited by 11
- 2023BIG-C: a Multimodal Multi-Purpose Dataset for Bembacited by 9
- 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Contextcited by 8
- 2022Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluationcited by 6
- 2022Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learningcited by 5
- 2024Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guidelinecited by 4
- 2025Voice of a Continent: Mapping Africa's Speech Technology Frontiercited by 4
- 2025Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languagescited by 3
- 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Reviewcited by 2
- 2026Sylber 2.0: A Universal Syllable Embeddingcited by 2
12 most cited of 14 All 14 (JSON)
- 2026AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages9 Apr 2026
- 2026Sylber 2.0: A Universal Syllable Embedding29 Jan 2026
- 2025Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review1 Oct 2025
- 2025Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages20 Jun 2025
- 2025Voice of a Continent: Mapping Africa's Speech Technology Frontier24 May 2025
- 2025Bemba Speech Translation: Exploring a Low-Resource African Language5 May 2025
- 2024The Zeno's Paradox of `Low-Resource' Languages28 Oct 2024
- 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialects27 Jun 2024
- 2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context2 Apr 2024
- 2024Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline26 Jan 2024
- 2023Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages7 Jun 2023
- 2023BIG-C: a Multimodal Multi-Purpose Dataset for Bemba26 May 2023
12 newest of 14 All 14 (JSON)