# Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities

arXiv: https://arxiv.org/abs/2207.11345 · HTML: https://mlsanity.com/paper/2207.11345/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing](https://mlsanity.com/paper/2001.00964/) (2020)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions](https://mlsanity.com/paper/2111.09983/) (2021)
- [Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance](https://mlsanity.com/paper/1908.08717/) (2019)
- [Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification](https://mlsanity.com/paper/2106.10826/) (2021)
- [ASR4REAL: An extended benchmark for speech models](https://mlsanity.com/paper/2110.08583/) (2021)
- [Comparing Human and Machine Errors in Conversational Speech Transcription](https://mlsanity.com/paper/1708.08615/) (2017)

## Built on by (most cited first, 28 of 28)

- [OpenAI's Approach to External Red Teaming for AI Models and Systems](https://mlsanity.com/paper/2503.16431/) (2025)
- [Towards measuring fairness in speech recognition: Fair-Speech dataset](https://mlsanity.com/paper/2408.12734/) (2024)
- [On the social bias of speech self-supervised models](https://mlsanity.com/paper/2406.04997/) (2024)
- [Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models](https://mlsanity.com/paper/2408.07665/) (2024)
- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [Improving Fairness and Robustness in End-to-End Speech Recognition through unsupervised clustering](https://mlsanity.com/paper/2306.06083/) (2023)
- [A Contrastive Learning Approach to Mitigate Bias in Speech Models](https://mlsanity.com/paper/2406.14686/) (2024)
- [Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features](https://mlsanity.com/paper/2309.07733/) (2023)
- [Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition](https://mlsanity.com/paper/2208.01157/) (2022)
- [Fairness of Automatic Speech Recognition: Looking Through a Philosophical Lens](https://mlsanity.com/paper/2508.07143/) (2025)
- [Improving Speech Recognition for African American English With Audio Classification](https://mlsanity.com/paper/2309.09996/) (2023)
- [DENOASR: Debiasing ASRs through Selective Denoising](https://mlsanity.com/paper/2410.16712/) (2024)
- [How to Evaluate Automatic Speech Recognition: Comparing Different Performance and Bias Measures](https://mlsanity.com/paper/2507.05885/) (2025)
- [Using Data Augmentations and VTLN to Reduce Bias in Dutch End-to-End Speech Recognition Systems](https://mlsanity.com/paper/2307.02009/) (2023)
- [WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing](https://mlsanity.com/paper/2506.22789/) (2025)
- [Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models](https://mlsanity.com/paper/2604.22631/) (2026)
- [Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation](https://mlsanity.com/paper/2605.07084/) (2026)
- [Cross-utterance ASR Rescoring with Graph-based Label Propagation](https://mlsanity.com/paper/2303.15132/) (2023)
- [CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition](https://mlsanity.com/paper/2502.01777/) (2025)
- [CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition](https://mlsanity.com/paper/2506.06071/) (2025)
- [Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTS](https://mlsanity.com/paper/2508.05102/) (2025)
- [Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition](https://mlsanity.com/paper/2602.01967/) (2026)
- [Where Do Self-Supervised Speech Models Become Unfair?](https://mlsanity.com/paper/2604.18249/) (2026)
- [Responsible Benchmarking of Fairness for Automatic Speech Recognition](https://mlsanity.com/paper/2605.10615/) (2026)
- [Elucidate Gender Fairness in Singing Voice Transcription](https://mlsanity.com/paper/2308.02898/) (2023)
- [Towards Fair ASR For Second Language Speakers Using Fairness Prompted Finetuning](https://mlsanity.com/paper/2510.18374/) (2025)
- ["OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection](https://mlsanity.com/paper/2604.05830/) (2026)
- [A Cross Community Agenda for Speech AI](https://mlsanity.com/paper/2609.13168/) (2026)

## Abstract (arXiv)

As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts. One approach to achieve fairness in speech recognition is to (1) identify speaker cohorts that suffer from subpar performance and (2) apply fairness mitigation measures targeting the cohorts discovered. In this paper, we report on initial findings with both discovery and mitigation of performance disparities using data from a product-scale AI assistant speech recognition system. We compare cohort discovery based on geographic and demographic information to a more scalable method that groups speakers without human labels, using speaker embedding technology. For fairness mitigation, we find that oversampling of underrepresented cohorts, as well as modeling speaker cohort membership by additional input variables, reduces the gap between top- and bottom-performing cohorts, without deteriorating overall recognition accuracy.