We’re definitely not close to done……. (hold your horses)
Quick documentation of how we’ve made certain decisions to add this feature as quickly as possible.
Continue Reading "Multiplayer Procedural Challenges & Convolving Feature Spaces"
I’ve been doing some research recently in Machine Learning. Resurrecting my previous “VertoPellis” project and cleaning up the source data we fed the system. Upon building the voice, we fed it speeches which had echos and high ambient noises.
Continue Reading "Rebuilding the Statistical Model with Cleaner Voice"
In preparation of subsequent blogs about my research in machine learning.
vertÅ (“‘turn’â€) + pellis ( “hideâ€) is Latin for Shapeshifter / Werewolf.
As its name denotes, it is a system that can mimic a sentient being starting with its voice and then visual features. It learns and assimilates from all types of relevant content. This can be but is not limited to phonic and visional content.
The grand vision is that it can be fed images, videos, and audio files of a subject and it would learn to mimic said subject through voice, visual etc.
Continue Reading "VertoPellis (“Shape Shifting”) Presentation"