Namarta Vij

Work place: Computer Science Department, University of Windsor, Canada



Research Interests: Computational Learning Theory


Namarta Vij is a graduate teaching assistant at the University of Windsor, Canada, where she also serves as a research assistant under the guidance of Dr. Ziad Kobti, the Director of the Computer Science Department at University of Windsor. With a strong academic background and industry experience, her research primarily revolves around recommender systems and machine learning, with a special focus on transformers. In addition to her academic pursuits, Namrata has successfully undertaken diverse projects for various companies. Recently, she demonstrated her expertise by developing a Web Server using ReactJS for the Cancer Research Centre of Marseille. 

Author Articles
An Experimental and Statistical Analysis to Assess impact of Regional Accent on Distress Non-linguistic Scream of Young Women

By Disha Handa Renu Vig Mukesh Kumar Namarta Vij

DOI:, Pub. Date: 8 Aug. 2023

Scream is recognized as constant and ear-splitting non-linguistic verbal communication that has no phonological structure. This research is based on the study to assess the effect of regional accent on distress screams of women of a very specific age group. The primary goal of this research is to identify the components of non-speech sound so that the region of origin of the speaker can be determined. Furthermore, this research can aid in the development of security techniques based on emotions to prevent and report criminal activities where victims used to yell for help. For the time being, we have limited the study to women because women are the primary victims of all types of criminal’s activities. The Non-Speech corpus has been used to explore different parameters of scream samples collected from three different regions by using high-reliability audio recordings. The detailed investigation is based on the vocal characteristics of female speakers. Further, the investigations have been verified with bi-variate, partial correlation and one-way ANOVA to find out the impact of region-based accent non-speech distress signal. Results from the correlation techniques indicate that out of four attributes only jitter varies with respect to the specific region. Whereas ANOVA depicts that there is no significant regional impact on distress non-speech signals.

[...] Read more.
Other Articles