Thesis supervisor: Gábor Gosztolya
Location of studies (in Hungarian): University of Szeged Abbreviation of location of studies: SZTE
Description of the research topic:
It is well-known that many neurogical and physical disorders change the speech of the subject (e.g. Alzheimer's Disease or Parkinson's Disease). Some such changes can be detected at a quite early stage, and a timely diagnosis might allow to slow the progress of the disease. In the recent years, researchers started paying attention to detect these slight changes by automatic techniques, which could be used for the automatic pre-screening of the possible patients in practice. Since the input of these methods is the speech of the subject, this area is considered as the sub-field of speech technology, and the employed techniques are frequently borrowed from similar areas, e.g. from automatic speech recognition or from speaker recognition. Still, as this area has a different goal, and any research should also meet the expectations of medical researches, the methods utilized usually have to be adapted, or even new algorithms or feature sets have to be developed. The task of the applicant is to get familiar with the technologies commonly used in medical speech processing, invent and develop new algorithms or feature sets, evalute the new ideas on the data sets available at the University, and finally to publish the new achievements.
Number of students who can be accepted: 1
Deadline for application: 2022-03-15
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
