# Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection

arXiv: https://arxiv.org/abs/2609.00276 · HTML: https://mlsanity.com/paper/2609.00276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Detecting cognitive decline using speech only: The ADReSSo Challenge](https://mlsanity.com/paper/2104.09356/) (2021)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions](https://mlsanity.com/paper/2302.11824/) (2023)
- [Universal Score-based Speech Enhancement with High Content Preservation](https://mlsanity.com/paper/2406.12194/) (2024)
- [Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement](https://mlsanity.com/paper/2001.10601/) (2020)
- [Multilingual Alzheimer's Dementia Recognition through Spontaneous Speech: a Signal Processing Grand Challenge](https://mlsanity.com/paper/2301.05562/) (2023)
- [Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline](https://mlsanity.com/paper/1803.10109/) (2018)
- [Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech](https://mlsanity.com/paper/2412.15772/) (2024)
- [HAFFormer: A Hierarchical Attention-Free Framework for Alzheimer's Disease Detection From Spontaneous Speech](https://mlsanity.com/paper/2405.03952/) (2024)
- [Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech](https://mlsanity.com/paper/2501.06727/) (2025)
- [Dementia Assessment Using Mandarin Speech with an Attention-based Speech Recognition Encoder](https://mlsanity.com/paper/2310.03985/) (2023)

## Abstract (arXiv)

Speech-based Alzheimer's disease (AD) detection increasingly relies on speech-enhanced and curated versions of the Pitt Corpus, where speech enhancement, sample selection, and demographic balancing are often treated as beneficial preprocessing steps. However, whether these transformations improve real-world AD detection or instead affect model generalization and prediction behavior remains unclear. In this work, we revisit the role of speech preprocessing and dataset curation across widely used benchmarks for speech-based AD detection. We evaluate the speech quality of different datasets, the cross-dataset generalization of multiple deep learning models under matched and mismatched enhancement settings, and the behavior of several recent large audio-language models (LALMs). Experimental results show that across multiple supervised speech models, speech-enhanced datasets often improve in-domain performance while reducing robustness in cross-domain evaluation. Matched enhancement between training and test data alleviates, but does not eliminate, this degradation. LALMs show a similar sensitivity: enhanced datasets induce stronger class imbalance and prediction shifts than unprocessed data. These results suggest that speech preprocessing and dataset curation can substantially influence downstream AD detection behavior, indicating that ``cleaner'' speech datasets are not necessarily more reliable for real-world AD detection.