<aside> 💡 Please visit https://sites.google.com/view/keonlee9420 for the recent update. (This page is no longer maintained by the author!)

</aside>

Hi there 👋 I am a deep learning researcher interested in everything towards Conversational AI, including Expressive Speech Synthesis, Generative Models, Natural Language Processing, and Representation Learning.

updated: March 29, 2024

My dream is to create an agent that can naturally communicate with humans with a unique personality (e.g., Samantha from the movie 『Her』). There are three considerations for this:

• A way of listening to human speech (speech-to-text)
• A way of thinking through human language (natural language processing)
• A way of speaking like a human (text-to-speech)

I'm currently working on text-to-speech (TTS) as my first goal since it is the most intuitive and efficient method to reveal a human-like personality.

Contact Information

📧 [email protected]

Github

https://github.com/keonlee9420

Google Scholar

LinkedIn

X (twitter)

Keon Lee (@keonlee9420) / X

Paper

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Jaehyeon Kim, Keon Lee, Seungjun Chung, Jaewoong Cho

ICLR 2024

[paper][demo]

Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

TaeHo Yoon, Kibeom Myoung, Keon Lee, Jaewoong Cho, Albert No, Ernest K. Ryu

NeurIPS 2023