Speech-based biomarking of heart failure
Bidragets beskrivning
Heart failure (HF) is a major public health problem affecting 25 million people worldwide. In this study, we will develop preventive healthcare technologies to detect HF from speech. This is feasible because speaker's state of health affects speech and therefore the state of health can be predicted from speech. Speech-based biomarking can be used to detect HF at an early stage by monitoring speech. We will study methods to parameterize the source of speech, the glottal flow, and use this information to build automatic speech-based biomarking systems capable of classifying HF patients from healthy controls and predicting the severity of HF. Data consists of speech recordings of healthy subjects and HF patients. The data will be used to build systems to biomark HF and to create an open evaluation environment for the estimation of the glottal flow. The project will be conducted at Aalto University jointly with Helsinki University Central Hospital and with three international units.
Visa merStartår
2020
Slutår
2024
Beviljade finansiering
Övriga uppgifter
Finansieringsbeslutets nummer
330139
Vetenskapsområden
El-, automations- och telekommunikationsteknik, elektronik
Forskningsområden
Signaalinkäsittely
Identifierade teman
cardiovascular diseases