Research
The EWA project focused on three key areas: data acquisition, speech parameter selection through data processing, and parameter evaluation to differentiate healthy speech from speech patterns indicative of cognitive impairment.
About EWA
-
Neurodegenerative diseases such as Alzheimer's and Parkinson's are a global health, economic and social threat. It is estimated that over 40 million people worldwide and over 60 000 in Slovakia are living with Alzheimer's disease and related disorders - the most common class of neurodegenerative diseases. This number is projected to rise dramatically in the coming years and decades. Unfortunately, there are currently no curative treatments for these diseases, and the underlying mechanisms remain largely unknown.
Symptoms of neurodegenerative diseases are also manifested in the manner and quality of the affected person's speech. Vocabulary may decrease, and speech may become slower and lose meaning, often described as 'empty.' That is why the team from AXON PRO undertook an innovative project to determine if speech analysis could identify symptoms of these diseases. We developed a mobile application that uses a playful approach to prompt users to describe images displayed on their phone. Modern smartphones are ideal for this purpose, nowadays even older people own them, or the mobile phones of younger relatives or acquaintances can be used.
-
This project represents an interdisciplinary research and development effort, bringing together the expertise of psychologists, neuroscientists, and various IT professionals to create a comprehensive application.
Data aquisiton
In collaboration with neurologists and psychologists, we developed a methodology for designing images appropriate for the study, determining key recording characteristics, categorizing data from healthy and sick individuals, and continuously optimizing this process. To facilitate data collection, we subsequently developed an intuitive application for recording participants' speech descriptions of the images.
Data processing
Spontaneous speech goes beyond just words. Laughter, hesitations, coughs, pauses – these all play a part. Annotation means the manual transcription of a vocal utterance into a text, with these accompanying sounds indicated. Annotation is one of the stages in the preparation of an artificial intelligence tool for speech to text - ASR (Automatic Speech Recognition). Subsequently, the speech utterances were subjected to acoustic analysis, which extracted hundreds of parameters such as length, volume, different types of frequencies, voice color, and others from the audio recordings. From the linguistic analysis, the so-called NLP (Natural Language Processing) parameters such as the number of full-meaning words, different word types, various lexical and semantic parameters were determined.
Evaluation of parameters
From one recording that contained descriptions of 65 images, i.e. 65 different speech utterances, over 100,000 parameters were generated and used in various computer algorithms and artificial intelligence methods such as linear regression, Random Forest and neural networks. By leveraging these algorithms and the knowledge of whether the speaker was healthy or diagnosed, the research achieved a high level of computer accuracy in differentiating between healthy and impaired speech. Additionally, the study revealed interesting statistical characteristics.