# Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus

arXiv: https://arxiv.org/abs/2112.06199 · HTML: https://mlsanity.com/paper/2112.06199/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition](https://mlsanity.com/paper/2005.07973/) (2020)
- [CNN depth analysis with different channel inputs for Acoustic Scene Classification](https://mlsanity.com/paper/1906.04591/) (2019)
- [Accent Recognition with Hybrid Phonetic Features](https://mlsanity.com/paper/2105.01920/) (2021)

## Built on by (most cited first, 4 of 4)

- [AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR](https://mlsanity.com/paper/2310.00274/) (2023)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages](https://mlsanity.com/paper/2303.12582/) (2023)

## Abstract (arXiv)

This paper describes foundational efforts with SautiDB-Naija, a novel corpus of non-native (L2) Nigerian English speech. We describe how the corpus was created and curated as well as preliminary experiments with accent classification and learning Nigerian accent embeddings. The initial version of the corpus includes over 900 recordings from L2 English speakers of Nigerian languages, such as Yoruba, Igbo, Edo, Efik-Ibibio, and Igala. We further demonstrate how fine-tuning on a pre-trained model like wav2vec can yield representations suitable for related speech tasks such as accent classification. SautiDB-Naija has been published to Zenodo for general use under a flexible Creative Commons License.