Publications by authors named "Tomoko Nabekura"
Article Synopsis
- This study investigates the use of deep neural networks (DNNs) to differentiate between speech patterns of patients with Parkinson's disease (PD) and spinocerebellar degeneration (SCD) using their speech data.
- It utilized speech recordings from 251 PD patients and 101 SCD patients to fine-tune a pre-trained DNN model that analyzed log-mel spectrograms to classify the speech data.
- The model demonstrated strong performance with an average AUC of 0.93, indicating it is an effective non-invasive tool for distinguishing between these neurodegenerative diseases, potentially useful in telemedicine applications.
