Our Technology
Following demos are showing our technologies and use cases
Control artificial
beings by text script
Anyone can write a script can control artificial beings and make them speak
Most existing artificial beings require voice actors, animators, or surrogate actors in the background to make them come alive. We are developing artificial intelligence technology to drive them through a text script.
Content expressions such as speech, face, gestures, etc are not simply mapped one-to-one from a given text. Human actor can act in different ways given a script. Our key technology is to generate speech and other expressions like professional actors by understanding various contextual information
Voice cloning and emotional speech synthesis
MBC Documentary “Meeting you“
AI rappers generated by prosody controllable speech synthesis technology
데이지(Dvzy)-Question
Du5t(더스트)-SUM
Generation of speech, facial expressions and gestures from a text script
CES2021
Cross lingual voice cloning and dubbing
Moon and Kim's voice in English
Morgan Freeman speaks Korean
Singing voice synthesis
BTS Fake love by Trump’s voic
Research papers
Cross-speaker Emotion Transfer by Manipulating Speech Style Latents
Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS
One-Shot Face Reenactment on Megapixels
EdiTTS: Score-based Editing for Controllable Text-to-Speech
MLP Singer - Towards Rapid Parallel Korean Singing Voice Synthesis
Diff-TTS - A Denoising Diffusion Model for Text-to-Speech
Large-scale Speaker Retrieval on Random Speaker-variability Subspace
Robust and Fine-grained Prosody Control of End-to-End Speech Synthesis
Voice Imitating Text-to-Speech Neural Networks
Learning Pronunciation from a Foreign Language in Speech Synthesis Networks
Emotional End-to-End Neural Speech Synthesizer