Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages

Claytone Sikasote, Kalinda Siaminwe, Stanly Mwape, Bangiwe Zulu, Mofya Phiri +4 more
6/7/2023
cs.CLcs.SDeess.AS

Official code: unza-speech-lab/zambezi-voice (22 stars, MIT, last commit 2024-10-09).

Abstract

This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours) and labelled data (over 80 hours) consisting of read speech recorded from text sourced from publicly available literature books. The dataset is created for speech recognition but can be extended to multilingual speech processing research for both supervised and unsupervised learning approaches. To our knowledge, this is the first multilingual speech dataset created for Zambian languages. We exploit pretraining and cross-lingual transfer learning by finetuning the Wav2Vec2.0 large-scale multilingual pre-trained model to build end-to-end (E2E) speech recognition models for our baseline models. The dataset is released publicly under a Creative Commons BY-NC-ND 4.0 license and can be accessed via https://github.com/unza-speech-lab/zambezi-voice .

View on arXivView PDF

Code Implementations(1)

unza-speech-lab/zambezi-voiceOfficial100%
MIT

Repository for multilingual speech data resources for native languages of Zambia.

229Aug 12, 20222 years agoMIT
low-resource-languagesspeech-recognitionspeech-to-textzambia

Similar Papers

AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages

88% match2026

Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data

87% match1 repo10.0k2023

Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning

86% match2022

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

86% match2 repos3112023

CL-MASR: A Continual Learning Benchmark for Multilingual ASR

86% match1 repo1402023

AudioPaLM: A Large Language Model That Can Speak and Listen

86% match2023

Cite this paper

@article{sikasote2023zambezi,
  title  = {Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages},
  author = {Claytone Sikasote and Kalinda Siaminwe and Stanly Mwape and Bangiwe Zulu and Mofya Phiri and Martin Phiri and David Zulu and Mayumbo Nyirenda and Antonios Anastasopoulos},
  year   = {2023},
  eprint = {2306.04428},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.04428v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.04428.svg)](https://codeofpaper.com/paper/2306.04428)

Discussion