Heeseung Kim

A look at new models for natural spoken responses.

VoiceTailor transforms TTS systems for efficient, personalized voice outputs.

Introducing NanoVoice, a quick and efficient text-to-speech model for personalized audio.

New model VoiceGuider improves TTS for diverse speakers.

Learn how new techniques help computers generate unique artistic images.

Learn how diptych prompting transforms text into stunning images.