Speech-based support system to monitor patients with Chronic Obstructive Pulmonary Disease

Patients with Chronic Obstructive Pulmonary Disease (COPD) suffer from voice changes differentlythan the healthy population. However, two questions remain to be studied: how long-term speech elements such as prosody are affected; and whether physical effort and medication also affect the speech of patients with COPD and, if so, how an automatic speech-based COPD detection system can be influenced by these changes.

The purpose of this research is to answer both issues. The COPD long reading speech and control groups were recorded, and the following experiments were performed: (a) a statistical analysis of groups of studies and control to analyze the effects of physical effort and speech medication; and (b) an automatic classification experiment to analyze how different recording conditions can affect the performance of a COPD detection system. The results obtained show that speech, especially prosodic features, is affected by physical effort and inhalation medication in both groups, although in opposite ways; and that the recording condition plays an important role in designing an automatic COPD detection system.

The current work takes a step forward in understanding speech in patients with COPD and in research into their automatic detection to help professionals monitor the patient's condition.

Check the paper at https://www.mdpi.com/2076-3417/11/17/7999/htm

  • Paper released at MDPI with the participation of the TIC Salut Social foundation within the Empoc project network.