# A Multimodal Framework for Dementia Detection via Linguistic and Acoustic Representation Learning

arXiv: https://arxiv.org/abs/2605.25540 · HTML: https://mlsanity.com/paper/2605.25540/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 20 of 20)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering](https://mlsanity.com/paper/1708.03619/) (2017)
- [BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection](https://mlsanity.com/paper/1902.00038/) (2019)
- [To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2008.01551/) (2020)
- [Comparing Acoustic-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2106.01555/) (2021)
- [Explainable Identification of Dementia from Transcripts using Transformer Networks](https://mlsanity.com/paper/2109.06980/) (2021)
- [Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech](https://mlsanity.com/paper/2106.09668/) (2021)
- [Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech](https://mlsanity.com/paper/2006.07358/) (2020)
- [ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Disease](https://mlsanity.com/paper/2310.15301/) (2023)
- [Detecting Dementia from Speech and Transcripts using Transformers](https://mlsanity.com/paper/2110.14769/) (2021)
- [Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech](https://mlsanity.com/paper/2412.15772/) (2024)
- [A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer](https://mlsanity.com/paper/2211.04368/) (2022)
- [Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech](https://mlsanity.com/paper/2501.06727/) (2025)
- [PROCESS-2: A Benchmark Speech Corpus for Early Cognitive Impairment Detection](https://mlsanity.com/paper/2605.14888/) (2026)
- [A Dual-Stage Time-Context Network for Speech-Based Alzheimer's Disease Detection](https://mlsanity.com/paper/2502.13064/) (2025)

## Abstract (arXiv)

Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the leading cause of dementia, affecting memory, reasoning, communication, and daily functioning. Early diagnosis is particularly important, as timely intervention may help slow cognitive decline and improve patient care. Recent studies have demonstrated that spontaneous speech contains valuable linguistic and acoustic biomarkers associated with dementia. However, existing approaches often rely on independently trained modality-specific models, feature concatenation strategies, ensemble methods, or attention-based fusion mechanisms that do not explicitly maximize the dependency between speech and transcript representations. In this work, we propose a multimodal deep learning framework for automatic dementia detection that jointly exploits speech and transcript information in an end-to-end trainable manner. Specifically, speech recordings are divided into 10-second segments and passed through a pre-trained HuBERT model to extract contextualized acoustic representations. To better capture informative temporal speech characteristics, attentive statistics pooling is employed to aggregate frame-level acoustic embeddings. For the textual modality, transcripts are encoded using a pre-trained BERT model, where the [CLS] token representation is used as the linguistic embedding. The acoustic and textual representations are subsequently combined using an attention-based Audio-Text Fusion (AT-Fusion) mechanism. In addition, we introduce a MINE objective to maximize the mutual information between modalities and improve multimodal representation alignment. The fused multimodal representation is finally used for dementia classification. Experiments conducted on the publicly available ADReSS Challenge and PROCESS-2 dataset demonstrate the effectiveness and robustness of the proposed approach for speech-based dementia assessment.