# The Voice of Equity: A Systematic Evaluation of Bias Mitigation Techniques for Speech-Based Cognitive Impairment Detection Across Architectures and Demographics

arXiv: https://arxiv.org/abs/2601.16989 · HTML: https://mlsanity.com/paper/2601.16989/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 69 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [Detecting cognitive decline using speech only: The ADReSSo Challenge](https://mlsanity.com/paper/2104.09356/) (2021)
- [FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion](https://mlsanity.com/paper/2210.15418/) (2022)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies](https://mlsanity.com/paper/2205.13421/) (2022)
- [The Impact of Speech Anonymization on Pathology and Its Limits](https://mlsanity.com/paper/2404.08064/) (2024)
- [Generative Emotional AI for Speech Emotion Recognition: The Case for Synthetic Emotional Speech Augmentation](https://mlsanity.com/paper/2301.03751/) (2023)
- [LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data](https://mlsanity.com/paper/2508.10027/) (2025)
- [Pathological voice adaptation with autoencoder-based voice conversion](https://mlsanity.com/paper/2106.08427/) (2021)
- [Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages](https://mlsanity.com/paper/2505.14874/) (2025)
- [Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies](https://mlsanity.com/paper/2509.03525/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection](https://mlsanity.com/paper/2606.27973/) (2026)
- [Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation](https://mlsanity.com/paper/2609.38976/) (2026)

## Abstract (arXiv)

Speech-based detection of cognitive impairment offers a scalable, non-invasive screening, yet algorithmic bias across demographic and linguistic subgroups remains critically underexplored. We present the first comprehensive fairness analysis framework for speech-based multi-class cognitive impairment detection, systematically evaluating bias mitigation across architectures, and demographic subgroups. We developed two transformer-based architectures, SpeechCARE-AGF and Whisper-LWF-LoRA, on the multilingual NIA PREPARE Challenge dataset. Unlike prior work that typically examines single mitigation techniques, we compared pre-processing, in-processing, and post-processing approaches, assessing fairness via Equality of Opportunity and Equalized Odds across gender, age, education, and language. Both models achieved strong performance (F1: SpeechCARE-AGF 70.87, Whisper-LWF-LoRA 71.46) but exhibited substantial fairness disparities. Adults >=80 showed lower sensitivity versus younger groups; Spanish speakers demonstrated reduced TPR versus English speakers. Mitigation effectiveness varied by architecture: oversampling improved SpeechCARE-AGF for older adults (80+ TPR: 46.19%=>49.97%) but minimally affected Whisper-LWF-LoRA. This study addresses a critical healthcare AI gap by demonstrating that architectural design fundamentally shapes bias patterns and mitigation effectiveness. Adaptive fusion mechanisms enable flexible responses to data interventions, while frequency reweighting offers robust improvements across architectures. Our findings establish that fairness interventions must be tailored to both model architecture and demographic characteristics, providing a systematic framework for developing equitable speech-based screening tools essential for reducing diagnostic disparities in cognitive healthcare.