Dementia represents a global public health concern, with the early detection of Alzheimer's disease, the most prevalent form of dementia, being of paramount importance. Given the limited availability of suitable biomarkers, research has shown that early cognitive impairment can be identified through patients' spoken language. This paper presents a multi-modal system for automatic Alzheimer's disease detection using speech. The system has been trained on spoken recordings of healthy individuals and Alzheimer's patients describing an image, a task requiring linguistic and cognitive skills. Built on fine-tuned advanced Large Language Models, audio feature extractors, and classifiers, the system, after an extensive comparison of single and multi-modal architectures, achieves optimal results with the combination of Mistral-7B, VGGish, and Support Vector Classifier, outperforming previous methods on the ADReSSo 2021 test set.

This paper proposes a procedure for facial template synthesis based on features extracted from multiple facial instances with varying pose. The proposed system extracts the rotation, scale and translation invariant SIFT features, also having high discrimination ability, from the frontal and half left and right profiles of an individual face images. These affine invariant features obviate the need of ad-hoc algorithms to register features of side profiles against frontal profiles for feature-set augmentation. An augmented feature set is then formed from the fusion of features from frontal and side profiles of an individual, after removing feature redundancy. The augmented feature sets of database and query images are matched using the Euclidean distance and Point pattern matching techniques. The experimental results are compared with the system using only frontal face images for both the matching strategies. The reported results prove the efficacy of the proposed system.