MétaCan
Menu
Back to cohort
Record W4414371545 · doi:10.1145/3769089

A Systematic Literature Review on Bias Evaluation and Mitigation in Automatic Speech Recognition Models for Low-Resource African Languages

2025· article· en· W4414371545 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueACM Computing Surveys · 2025
Typearticle
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsSystematic reviewAdversarial systemDiversity (politics)Languages of AfricaLinguistic diversity

Abstract

fetched live from OpenAlex

With recent advancements in speech recognition, it is crucial to ensure that automatic speech recognition (ASR) systems do not exhibit systematic biases, such as those related to gender, age, accent, and dialect. Although research has extensively examined systematic biases such as those related to gender, age, accent, and dialect, for high-resource languages, research on low-resource African languages remains limited. This systematic literature review synthesizes evidence on bias evaluation and mitigation in ASR models for African languages, adhering to the PRISMA reporting guidelines. Our analysis reveals that most biases stem from data imbalances and limited linguistic diversity in training datasets, resulting in disproportionately high error rates for underrepresented speaker groups. Mitigation strategies in African contexts have primarily focused on data-centric methods, including dataset expansion, augmentation, and transfer learning. In contrast, more advanced approaches, including fairness-aware modeling, bias-aware loss functions, adversarial debiasing, and speaker-adaptive techniques, are rarely applied. Gender, accent, and dialect biases dominate the few African studies available, while age and racial biases are almost absent. The limited number of African languages covered highlights the urgent need for more representative and inclusive research. Addressing these gaps will support the development of fairer and more robust ASR technologies across the continent.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.006
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.968
Threshold uncertainty score0.706

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0090.006
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.052
GPT teacher head0.320
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it