Investigating the Impact of Multilingual Pre-trained Speech Models on Gender Bias in ASR for Low Resource African Languages
- 25 November 2025
- book chapter
- Published by Springer Nature
- p. 144-158
Abstract
No abstract availableKeywords
This publication has 30 references indexed in Scilit:
- Uncovering Bias in ASR Systems: Evaluating Wav2vec2 and Whisper for Dutch speakers2023
- Towards inclusive automatic speech recognitionComputer Speech & Language, 2023
- Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models2023
- Hey ASR System! Why Aren’t You More Inclusive?2022
- Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models2022
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Racial disparities in automated speech recognitionProceedings of the National Academy of Sciences, 2020
- Deep multimodal semantic embeddings for speech and images2015
- Connectionist temporal classification2006
- Use of Ranks in One-Criterion Variance AnalysisJournal of the American Statistical Association, 1952