AAII Technical Lecture Series (ATLS-14)
Title: Machine learning for clinical speech processing
Abstract:
Speech technology is used to diagnose the anatomical and functional defects associated with the speech production system. The use of speech processing-based systems provides objective evaluation results and can be used as assistive tools by clinians. This talk provides an overview of clinical perspectives of automated speech evaluation and the development of clinical speech databases. Further, the applications of machine learning techniques for the automatic evaluation of dysarthric and cleft palate disorders will be discussed.
Speaker
Dr. Vikram C. Mathad is working as Research Scientist at zapr media labs, Bangalore. He received the B.E. degree in Electronics and Communication Engineering (ECE) from PESIT, South Campus, Bengaluru, India, in 2011, the M.Tech. degree in biomedical signal processing and instrumentation from SJCE, Mysuru, India, in 2013 and Ph.D degree in Electronics and Electrical Engineering (EEE) from the Indian Institute of Technology Guwahati (IITG), Guwahati, India, in 2019. His thesis work was focused on the automatic detection of misarticulated consonants. He was working as a Postdoctoral Researcher in the Department of Speech and Hearing Science, Arizona State University, Tempe, Arizona, USA, where his work involves in the development of speech-based objective assessment methods for cleft lip and palate, dysarthria, and Alzheimer’s disorders. He also worked for the funded projects sponsored by the Ministry of Human Resource and Development (MHRD)-India, Department of Biotechnology (DBT)-India, and National Institute of Health (NIH)-USA. His research interests include speech signal processing, biomedical signal processing, and machine learning.
Contact:
Title: Machine learning for clinical speech processing
Speaker name: Vikram C. Mathad, PhD (IITG), Post-doc (Arizona State University, USA), Research Scientist at zapr media labs, Bangalore
Date: 12 March 2022
Time: 5 PM (IST)