AI Helps Protect Endangered Elephants

Artificial Intelligence, Features, Cloud, Computer Vision & Machine Vision, Machine Learning & Artificial Intelligence, Signal/Audio Processing, Speech & Audio Processing

Nadeem Mohammad, posted Sep 10 2018

According to the U.N., up to 100 elephants are slaughtered every day in Africa by poachers taking part in the illegal ivory trade.

Read more

AI Can Help Anyone Become a Beatbox Champion

Artificial Intelligence, Computer Vision & Machine Vision, Machine Learning & Artificial Intelligence, Quadro, Signal/Audio Processing, Speech & Audio Processing

Nadeem Mohammad, posted Aug 10 2018

To help up-and-coming musicians create the best beats for their song, developers from a Japanese-based AI startup developed a deep learning system called Neural Beatboxer that can convert everyday sounds into hours of automatically compiled rhythm

Read more

AI Can Play It By Ear

Artificial Intelligence, cuDNN, Machine Learning & Artificial Intelligence, Signal/Audio Processing, Speech & Audio Processing, Tesla

Nadeem Mohammad, posted May 22 2018

Researchers from Facebook developed a deep learning system that can replicate the music it hears and play it back as if it were Mozart, Beethoven, or Bach.

Read more

New Speech Synthesis System Can Imitate Thousands of Accents

Artificial Intelligence, GeForce, Machine Learning & Artificial Intelligence, Signal/Audio Processing, Tesla

Nadeem Mohammad, posted Oct 24 2017

Baidu announced their latest production-quality speech synthesis system that can imitate thousands of human voices from people across the globe.

Read more

Generating Expressive 3D Facial Animations From Audio

Events, Research, cuDNN, GeForce, Machine Learning & Artificial Intelligence, Media & Entertainment, Signal/Audio Processing

Nadeem Mohammad, posted Jul 26 2017

Researchers from NVIDIA and the independent game developer Remedy Entertainment developed an automated real-time deep learning technique to create 3D facial animations from audio with low latency.

Read more

AI Learns to Lip-Sync From Audio Clips

Research, cuDNN, GeForce, Higher Education/Academia, Image Recognition, Media & Entertainment, Signal/Audio Processing, Virtual Reality

Nadeem Mohammad, posted Jul 12 2017

University of Washington researchers developed a deep learning-based system that converts audio files into realistic mouth shapes, which are then grafted onto and blended with the head of that person from another existing video.

Read more