Creative performances that would have never been possible before, such as transforming a performing instrument into a completely different sound, or transforming one’s voice into that of a celebrity are now possible.
Automatically correct acoustic environment such as noise and echoes that have been difficult to remove using conventional methods.
We offer Neutone, a platform for deep learning-based audio plug-ins that enables real-time timbre conversion and acoustic processing.
This technology is divided into a plugin for real-time audio processing and a modeling part for processing using deep learning. The plugin is compatible with the VST3 and AU formats and can be used with general-purpose DAW (Digital Audio Workstation) interfaces, PCs, smartphones, and other devices. The modeling part applies a learning architecture that combines variational autoencoders with adversarial learning. The encoder layer expands the input sound into the latent space, “interprets” it, and then controls the decoder layer to reconstruct the target sound.
Get in touch with us here!