Microsoft’s new VALL-E “neural codec language model” can closely simulate a person’s voice when given just a three-second audio sample, and once it learns a specific voice, it can synthesise audio of that person saying anything, including with the right emotional tone. Pair VALL-E with another generative AI models such as GPT-3 and you have a content […]
The highly-valued startup behind popular text-to-image generator Dall-E, OpenAI ,has announced the release of Point-E, which can produce 3D point clouds directly from text prompts in a minute or two using a computer with a sufficiently powerful GPU. How is it done? “To produce a 3D object from a text prompt, we first sample an image […]
This AI-powered experiment by synth hardware brand Teenage Engineering and design studios Modern and Bureau Cool creates kaleidoscopic visual landscapes for composed music. The work, which uses Teenage Engineering’s OP-Z sequencer and translates the musical output into art in real-time, is inspired by the neurological condition synesthesia, where the brain perceives sensory input for several […]
Sony’s fifth generation Alpha camera, the a7R V, contains a big technological advance – a dedicated deep learning chip that recognises humans and animals in real-time. It achieves pin-sharp autofocus on a subject’s eye by tracking its entire body even when it is in motion. This works when a subject’s eye is only partly visible. […]
Using machine learning-based tools, Lorenzo Folli and Olga Shirnina of Mystery Scoop have a put together a collection of digitally restored 19th Century that then appear to come to life as the camera lingers and subtly moves across them. Wonderful!
Text-to-speech has been around for years, but quality limitations meant they were used primarily by voice assistants and chat bots. Developments in AI and deep learning now make it possible to create synthetic voices that have the prosody and pronunciation of human speech. Traditional voiceover and dubbing markets are predicated to generate a total of […]