Share Profile
MARINA SHEHZAD
Aspiration Statement
“I want to pursue my postgraduate studies in Data Science/Analysis. As a career, I am inclined towards the same field - practising would help me gain a better understanding of the domain. Interested in technical research (in DS or AI/ML) as well. My other passions include reading, creative writing, swimming and cycling.”
Core Skills
- Python
- C++
- MYSQL
- NetLogo
- LateX
- MS Office
- ModelSim
- Research
Experience
Leadership / Meta-curricular
- Microsoft Certification in “Developing Windows Apps using HTML, CSS and JavaScript”
- Content Writer - Paper Plane (May 2014 - Jul 2014)
- Research Assistant - Habib University (Dec 2016 - Jan 2017)
Internship / Volunteer Work
- Product Manager II - SadaPay (Nov 2021 - Present)
- Assistant Manager [Product] - Salesflo (Jul 2020 - Nov 2021)
- Veritas Learning Circle - Curriculum Developer
- The Citizen’s Foundation - Mathematics teacher
Publications / Creative Projects
- Object Oriented Programming: Project: Galactic Enforcers in C++ using SDL 2.0
- Artificial Intelligence: Project: Be My Eyes (Interact with the visually impaired to help identify objects)
- Technology, Management, & Entrepreneurship: Project: Khuahish (Digital platform for literacy)
Final Year Project
Project Title
Personalized Audio Stories
Description
Our FYP proposes a CNN-based neural style transfer to make storytelling personalized by asking users to record a few sentences that are used to mimic their voice. User audios are converted to spectrograms, the style of which is transferred to the spectrogram of a base voice narrating the story. This approach stands out as it needs a small dataset and therefore, also takes less time. Working parents are also increasingly concerned about the minimal time that they spend with their children and of the unhealthy use of smart devices by their children. This addresses both these problems while reviving the storytelling culture in a medium relevant to children. While storytelling is an excellent application of this work given the voice generated preserves emotion, this can be extended to more domains. The personalized voice can be used in chatbots/personal assistants making them a lot less robotic. (Group Project)
Project Pictures