AI for Creators
Discovering new pathways for AI to enhance the creative pursuits of artists and
creators of all kinds, enabling rich experiences and undiscovered avenues
for creative human pursuits from visual arts, sound and music.
Our Approach
Current research is focused on where AI can impact various mediums to increase creative and artistic capacity in all dimensions. Across several research areas we are committed to supporting creators and exploring technology that can serve as a foundation for human creativity. We are working towards the controllability and real-time functionality of AI foundation models with efficiency and speed for editing, restoration, creation, and the fine grain control needed by professional creators in music, sound, 2D and 3D.
Latest Publications
Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between re…
Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for making high-fidelity recon…
Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between re…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
