Computer Vision, Machine Learning | AI avatar for talent matching platform
Project scope
Categories
UX design Market research Machine learning Artificial intelligenceSkills
speech recognition machine learning lip sync computer vision artificial intelligenceBuild a 3D avatar interview system that records a video, and then mimics /repeats the narration.
Build a 3D avatar interview system that records a video, and then mimics /repeats the narration.
Extract speech from any recorded/live video.
convert it speech to text
convert text to speech
live lip syncing
3d Avatar speaking to what was being said in the video.
The final deliverables should take the form of:
A final report of outcome
A 30-minute presentation
All codes/material/assets to be shared with employer
Students will connect directly with the employer for mentorship and supervision throughout the project.
About the company
NeedSpot is AI talent matching platform. NeedSpot’s mission is to provide best user experience to candidates looking for job in tech industry who are coming straight out of college.
Many graduates don’t know which is the best suited job position for them. Imagine instead of taking weeks of searching jobs online or through your academic institutions career centre, opportunities simply come your way knocking on your career door. Regardless of what you look or sound like, your gender, racial, religious identity, everyone gets fair and equal chance.