BembaSpeech: A Speech Recognition Corpus for the Bemba Language

Claytone Sikasote, Antonios Anastasopoulos


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.
Anthology ID:
2022.lrec-1.790
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
7277–7283
Language:
URL:
https://aclanthology.org/2022.lrec-1.790
DOI:
Bibkey:
Cite (ACL):
Claytone Sikasote and Antonios Anastasopoulos. 2022. BembaSpeech: A Speech Recognition Corpus for the Bemba Language. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7277–7283, Marseille, France. European Language Resources Association.
Cite (Informal):
BembaSpeech: A Speech Recognition Corpus for the Bemba Language (Sikasote & Anastasopoulos, LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.790.pdf
Code
 csikasote/BembaSpeech +  additional community code
Data
JW300