A Hybrid Approach for Parkinson’s Disease diagnosis with Resonance and Time-Frequency based features from Speech signals

作者：

Highlights：

• A hybrid approach is proposed to diagnose Parkinson’s disease using speech signals.

• It combines resonating and time-frequency components for robust feature extraction.

• Potential of Convolutional Neural Networks for voice signal analysis is explored.

• Impact of diversity is analyzed for validation of proposed work in clinical use.

摘要

•A hybrid approach is proposed to diagnose Parkinson’s disease using speech signals.•It combines resonating and time-frequency components for robust feature extraction.•Potential of Convolutional Neural Networks for voice signal analysis is explored.•Impact of diversity is analyzed for validation of proposed work in clinical use.

论文关键词：Parkinson’s disease,Voice disorder,Resonance based components,RSSD,PSD,CNN,Diversity

论文评审过程：Received 8 January 2021, Revised 3 April 2021, Accepted 22 May 2021, Available online 29 May 2021, Version of Record 4 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115283