2 code implementations • 24 Feb 2023 • Junhyeok Lee, Wonbin Jung, Hyunjae Cho, Jaeyeon Kim, Jaehwan Kim
Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech.
no code implementations • IEEE International Conference on Image Processing (ICIP) 2021 • Jaehwan Kim, Soo Min Kang, Kwang Pyo Choi, Youngo Park, Chaeeun Lee, JongSeok Lee
In this paper, an unsupervised image downscaler that preserves the high frequency content of the original image based on an autoencoder is presented.