Speaker: Ajinkya Kulkarni
Date: February 14, 2019 at 10:30 – C005
Recently, Generative FLOW based architecture have been proposed for generating high quality image generation. The major challenges in machine learning domain are ability to learn the representation from few data points and ability to generate new data from learned representation. In this talk, we will discuss both of these aspects with Generative FLOW architectures and how it can be used to model speech with the help of deep neural architectures such as Wavenet.