Project: The goal is to create a machine learning algorithm that would 1) eliminate background noise from speech 2) transform accented speech into non accented. We already have a dataset for this project.
The business/team: We are a team of Stanford Engineers, creating an early stage startup that aims to create a sound-enhancing software for greater clarity during calls.
Capabilities and experience needed: Looking for an experienced data scientist.
22 freelancers are bidding on average $801 for this job
Hello! I'd like to deliver unsupervised noise reduction model with accent alteration. I'm familiar with WaveNet, Mel Spectrogram, pytorch and GAN architecture. I'll do the job blazingly fast. Please, give me a try!
Hi dear I have many experience in ML and Deep learning. I have made many programs with python/C#/c++/tensorflow for audio and image processing so I can help you perfectly good luck