Sidebar Menu

Team

   Professors
   External Lecturers
   Office Assistance
   System Administration
   Internal PhD Students
   External PhD Students
   Students
   Alumni
   Company Founders
   DSS Cups

Research

   Research Topics
   Real-time Framework
   Publications

Teaching

   Lectures
   Labs
   Seminars
   Student Projects
   Theses
   Evaluations
   Exams
   RED

News

Events

   Talks

Media Center

   Audio Examples   
   Data Bases
   Surveys

GaS

   Basic Information
   Prices
   Members
   Reports
   Statute

 

M. Sc. Finn Spitz

Room D-019
Kaiserstraße 2, 24143 Kiel, Germany
Phone: +49 431 880-6132 
Telefax: +49 431 880-6128
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Research: Speech Analysis and Therapy for Parkinson Patients

The Parkinson’s disease is one of the most common central nervous system disorders and in Germany alone are approximately 300000 citizens affected. Medication and therapies can be used to treat the symptoms of the motor system. But there are often speech disorders, like a monotone, mumbling voice, silent speaking and amplified breath sounds, which can only be treated by a therapy by logopedics.

To support this therapy and to be able to measure the speech quality of the patients in their daily routine, a possibility is examined, to design a speech quality estimation using a hearing aid device. The corresponding signal processing is implemented in parallel on a mobile phone to the algorithms of the hearing aid device. As result a value is computed, which can be used to distinguish, whether the speech level is high enough and the speech is understandable.

An iPhone app is developed, to implement the needed signal processing on a mobile phone. The app is designed to fulfill different test scenarios to support the speech therapy or examine the current speech quality in realtime.

To analyze the speech correctly, the system is controlled by an own voice detection and noise is reduced. Through pattern recognition different features are extracted, to be able to analyze the speech using a classifier. The classifier can consist of multiple GMMs or a neuronal net.

 

Related topics:

  • Speech analysis
  • Pattern recognition
  • App development
  • Realtime digital signal processing
  • Neural networks

 

Further interests:

  • Real-time digital signal processing
  • Noise estimation
  • Adaptive filters

 

Short CV

 
 
Time span   Details  
  2018 - current   Research assistant at the Christian-Albrechts-Universität zu Kiel, Kiel, Germany  
  2015 - 2017   M.Sc. in Electrical and Information Engineering
Christian-Albrechts-Universität zu Kiel, Germany
 
  2014 - 2015   Internship (R&D) at Olympus Surgical Technologies Europe
Hamburg, Germany
 
  2011 - 2015   B.Sc. in Electrical and Information Engineering
Christian-Albrechts-Universität zu Kiel, Germany
 

 

Publications

  1.    

    F. Spitz, C. Baasch, G. Schmidt, U. Heute, A. Nebel, G. Deuschl: Hörgeräte-basierte Parkinson-Sprachanalyse, Proc. DAGA, Germany, 2018