# False positive bias in AI-powered speech-based cognitive screening for multilingual English speakers in the UK

arXiv: https://arxiv.org/abs/2602.13047 · HTML: https://mlsanity.com/paper/2602.13047/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 73 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [Multilingual Alzheimer's Dementia Recognition through Spontaneous Speech: a Signal Processing Grand Challenge](https://mlsanity.com/paper/2301.05562/) (2023)
- [CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech](https://mlsanity.com/paper/2407.13660/) (2024)
- [Early Dementia Detection Using Multiple Spontaneous Speech Prompts: The PROCESS Challenge](https://mlsanity.com/paper/2412.15230/) (2024)
- [CognoSpeak: an automatic, remote assessment of early cognitive decline in real-world conversational speech](https://mlsanity.com/paper/2501.05755/) (2025)
- [MultiConAD: A Unified Multilingual Conversational Dataset for Early Alzheimer's Detection](https://mlsanity.com/paper/2502.19208/) (2025)

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

- [PROCESS-2: A Benchmark Speech Corpus for Early Cognitive Impairment Detection](https://mlsanity.com/paper/2605.14888/) (2026)
- [CCMAN: Cognitive Instability-Aware Cross-Modal Attention Network for Interpretable Temporal Biomarkers of Verbal Fluency Speech](https://mlsanity.com/paper/2609.14764/) (2026)

## Abstract (arXiv)

Conversational speech reveals early signs of cognitive decline, including dementia and mild cognitive impairment (MCI). AI models show promise for speech-based screening, yet most research focuses on monolingual groups. In the UK, dementia is projected to rise fastest among Black and Asian communities, where multilingualism is common, making equity assessment critical. We recruited 1,395 participants (monolingual English speakers and multilingual speakers from Sheffield/Bradford) and collected over 263 hours of speech via the CognoMemory agent. Multilingual participants spoke English alongside Somali, Chinese, or South Asian languages (Hindi, Urdu, Punjabi, Mirpuri, Arabic). We evaluated ASR (Whisper, Wav2Vec 2.0, NeMo) and downstream AI models for cognitive classification and MMSE regression. ASR accuracy showed no significant differences across groups. However, downstream models exhibited systematic disparities: multilingual speakers were more often misclassified as impaired, especially in memory, fluency, and reading tasks. False-positive rates were substantially higher for multilingual (28 to 37%) than monolingual (12 to 16%) speakers, meaning multilingual individuals were approximately 2.5 times more likely to receive incorrect impairment labels. These biases worsened when models were trained on DementiaBank. This is the first large-scale analysis of false-positive bias in speech-based AI cognitive screening for UK multilingual ethnic minorities. Despite strong overall performance, current models show measurable disparities affecting multilingual speakers. Addressing these biases is essential for safe, equitable deployment in diverse healthcare settings.