@misc{radford2022whisper,
  doi = {10.48550/ARXIV.2212.04356},
  url = {https://arxiv.org/abs/2212.04356},
  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@inproceedings{sikasote-etal-2023-big,
    title = "{BIG}-{C}: a Multimodal Multi-Purpose Dataset for {B}emba",
    author = "Sikasote, Claytone  and
      Mukonde, Eunice  and
      Alam, Md Mahfuz Ibn  and
      Anastasopoulos, Antonios",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.115",
    doi = "10.18653/v1/2023.acl-long.115",
    pages = "2062--2078",
    abstract = "We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the {``}traditionally{''} used high-resourced ones. All data and code are publicly available: [\url{https://github.com/csikasote/bigc}](\url{https://github.com/csikasote/bigc}).",
}

@InProceedings{sikasote-anastasopoulos:2022:LREC,
  author    = {Sikasote, Claytone  and  Anastasopoulos, Antonios},
  title     = {BembaSpeech: A Speech Recognition Corpus for the Bemba Language},
  booktitle      = {Proceedings of the Language Resources and Evaluation Conference},
  month          = {June},
  year           = {2022},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {7277--7283},
  abstract  = {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 explored different approaches; supervised pre-training (training from scratch), cross-lingual transfer learning from a monolingual English pre-trained model using DeepSpeech on the portion of the dataset and fine-tuning large scale self-supervised Wav2Vec2.0 based multilingual pre-trained models on the complete BembaSpeech corpus. From our experiments, the 1 billion XLS-R parameter model gives the best results. The model achieves a word error rate (WER) of 32.91\%, results demonstrating that model capacity significantly improves performance and that multilingual pre-trained models transfers cross-lingual acoustic representation better than monolingual pre-trained English model on the BembaSpeech for the Bemba ASR. Lastly, results also show that the corpus can be used for building ASR systems for Bemba language.},
  url       = {https://aclanthology.org/2022.lrec-1.790}
}