# AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents

arXiv: https://arxiv.org/abs/2402.01152 · HTML: https://mlsanity.com/paper/2402.01152/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Multilingual Speech Recognition With A Single End-To-End Model](https://mlsanity.com/paper/1711.01694/) (2017)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR](https://mlsanity.com/paper/2303.18110/) (2023)
- [KinyaBERT: a Morphology-aware Kinyarwanda Language Model](https://mlsanity.com/paper/2203.08459/) (2022)
- [Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data](https://mlsanity.com/paper/2205.08014/) (2022)
- [Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings](https://mlsanity.com/paper/2110.03520/) (2021)
- [Accented Speech Recognition: A Survey](https://mlsanity.com/paper/2104.10747/) (2021)
- [E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition](https://mlsanity.com/paper/2106.08211/) (2021)
- [Quantifying Language Variation Acoustically with Few Resources](https://mlsanity.com/paper/2205.02694/) (2022)
- [Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification](https://mlsanity.com/paper/2102.07370/) (2021)
- [Black-box Adaptation of ASR for Accented Speech](https://mlsanity.com/paper/2006.13519/) (2020)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation](https://mlsanity.com/paper/2110.04908/) (2021)
- [Semi-supervised and Active-learning Scenarios: Efficient Acoustic Model Refinement for a Low Resource Indian Language](https://mlsanity.com/paper/1810.06635/) (2018)

## Built on by (most cited first, 3 of 3)

- [1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis](https://mlsanity.com/paper/2406.11727/) (2024)
- [WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing](https://mlsanity.com/paper/2509.18004/) (2025)
- [Culture Cartography: Mapping the Landscape of Cultural Knowledge](https://mlsanity.com/paper/2510.27672/) (2025)

## Abstract (arXiv)

Despite advancements in speech recognition, accented speech remains challenging. While previous approaches have focused on modeling techniques or creating accented speech datasets, gathering sufficient data for the multitude of accents, particularly in the African context, remains impractical due to their sheer diversity and associated budget constraints. To address these challenges, we propose AccentFold, a method that exploits spatial relationships between learned accent embeddings to improve downstream Automatic Speech Recognition (ASR). Our exploratory analysis of speech embeddings representing 100+ African accents reveals interesting spatial accent relationships highlighting geographic and genealogical similarities, capturing consistent phonological, and morphological regularities, all learned empirically from speech. Furthermore, we discover accent relationships previously uncharacterized by the Ethnologue. Through empirical evaluation, we demonstrate the effectiveness of AccentFold by showing that, for out-of-distribution (OOD) accents, sampling accent subsets for training based on AccentFold information outperforms strong baselines a relative WER improvement of 4.6%. AccentFold presents a promising approach for improving ASR performance on accented speech, particularly in the context of African accents, where data scarcity and budget constraints pose significant challenges. Our findings emphasize the potential of leveraging linguistic relationships to improve zero-shot ASR adaptation to target accents.