Parkinson Disease Classification with Voice Recordings and Convolutional Neural Networks

The paper presents a novel way for detection parkinson's disease detection. The proposed approach uses the combination of deep neural networks and Long short-term memory (LSTM) with much enhanced speech signals. Signals obtained through the technique called Mode Decomposition (MD). As compared with the literature mentioned, a better classification result is achieved through proposed method, The method demonstrates its potential and way to early detect the Parkinson disease and reducing the impact of speech disorders caused by the disease.