Your Daily AI Research tl;dr — 2022–10–27 🧠

Shutterstock will start selling DALLE-generated images through a partnership with OpenAI! (and some speech-to-speech and speech synthesis amazing papers!)

Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals 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.

Receive your daily update right in your inbox ⬇️

1️⃣ Improving Speech-to-Speech Translation Through Unlabeled Text

“We propose an effective way to utilize the massive existing unlabeled text from different languages to create a large amount of speech-to-speech translations (S2ST) data to improve S2ST performance by applying various acoustic effects to the generated synthetic data.”

Link to the paper: https://arxiv.org/abs/2210.14514

2️⃣ Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network