User Engagement Research


Understanding, predicting and enhancing user engagement with entertainment content, using data generated by entertainment ecosystems and state-of-the-art AI technologies, thus helping creators understand their customers better and enabling organizations to become data-driven companies.
Our Approach
Our research is focused on creating AI technologies to capture the complexities of how users engage with entertainment content. Motivated by the insight that user engagement is a fundamental concept that transcends content type, culture, user interface, and use case, we aim to transform the entertainment business by creating a User Engagement Foundation Model using engagement data from different entertainment platforms, and reducing the effort required for multiple downstream tasks such as real-time recommendation, customer segmentation, hyper-personalization, and churn prevention. We aim to use the foundation model along with LLMs and flexible natural language interfaces to effortlessly provide insights to business users as well as content creators about their customers and content.
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…
Latest Blog

Unlocking the Future of Video-to-Audio Synthesis: Inside the MMAudio Model
In a world increasingly driven by multimedia content, AI researchers have long struggled to generate high-quality, synchronized audio from video. Recently, audio generation models …

Revolutionizing Creativity with CTM and SAN: Sony AI's Groundbreaking Advances …
In the dynamic world of generative AI, the quest for more efficient, versatile, and high-quality models continues to push forward without any reduction in intensity. At the forefro…
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.