Your Daily AI Research tl;dr — 2022–06–29 🧠

Welcome to your official daily AI research tl;dr (often with code and news) for AI enthusiasts where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating. I will also take this opportunity to share daily exciting news in the field.

Let’s get started with this iteration!

1️⃣ Video2StyleGAN: Encoding Video in Latent Space for Manipulation

A new approach leveraging StyleGAN for semantic face video manipulation reusing the high-resolution portion of the latent vector to enforce temporal consistency and capturing subtle face motions and expressions with novel losses that involve sparse facial landmarks and dense 3D face mesh

Link to the paper: https://arxiv.org/abs/2206.13078

2️⃣ CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer

The abstract is simply perfect: “a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually appropriate prosody, and c) transferring prosody at fine-grained level between any pair of seen…