# Alzheimer's Disease Detection from Spontaneous Speech through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models

arXiv: https://arxiv.org/abs/2106.08689 · HTML: https://mlsanity.com/paper/2106.08689/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 16 Jun 2021.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [ERNIE 2.0: A Continual Pre-training Framework for Language Understanding](https://mlsanity.com/paper/1907.12412/) (2019)
- [A Convolutional Neural Network for Modelling Sentences](https://mlsanity.com/paper/1404.2188/) (2014)
- [Detecting cognitive decline using speech only: The ADReSSo Challenge](https://mlsanity.com/paper/2104.09356/) (2021)
- [To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2008.01551/) (2020)
- [Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic review](https://mlsanity.com/paper/2010.06047/) (2020)
- [Multi-Layer Ensembling Techniques for Multilingual Intent Classification](https://mlsanity.com/paper/1806.07914/) (2018)
- [Dependency-based Convolutional Neural Networks for Sentence Embedding](https://mlsanity.com/paper/1507.01839/) (2015)

## Built on by (most cited first, 13 of 13)

- [Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features](https://mlsanity.com/paper/2204.04629/) (2022)
- [Exploring linguistic feature and model combination for speech recognition based automatic AD detection](https://mlsanity.com/paper/2206.13758/) (2022)
- [LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data](https://mlsanity.com/paper/2508.10027/) (2025)
- [Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection](https://mlsanity.com/paper/2210.16539/) (2022)
- [Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech](https://mlsanity.com/paper/2305.16406/) (2023)
- [Evaluating Spoken Language as a Biomarker for Automated Screening of Cognitive Impairment](https://mlsanity.com/paper/2501.18731/) (2025)
- [A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities](https://mlsanity.com/paper/2409.19737/) (2024)
- [Performance Assessment of ChatGPT vs Bard in Detecting Alzheimer's Dementia](https://mlsanity.com/paper/2402.01751/) (2024)
- [Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection](https://mlsanity.com/paper/2412.06332/) (2024)
- [Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies](https://mlsanity.com/paper/2509.03525/) (2025)
- [Explainable cognitive decline detection in free dialogues with a Machine Learning approach based on pre-trained Large Language Models](https://mlsanity.com/paper/2411.02036/) (2024)
- [Exploring Hybrid and Ensemble Models for Multiclass Prediction of Mental Health Status on Social Media](https://mlsanity.com/paper/2212.09839/) (2022)
- [Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection](https://mlsanity.com/paper/2606.31186/) (2026)

## Abstract (arXiv)

In this paper, we combined linguistic complexity and (dis)fluency features with pretrained language models for the task of Alzheimer's disease detection of the 2021 ADReSSo (Alzheimer's Dementia Recognition through Spontaneous Speech) challenge. An accuracy of 83.1% was achieved on the test set, which amounts to an improvement of 4.23% over the baseline model. Our best-performing model that integrated component models using a stacking ensemble technique performed equally well on cross-validation and test data, indicating that it is robust against overfitting.