no code implementations • 21 Mar 2024 • Dougho Park, Younghun Kim, Harim Kang, Junmyeoung Lee, Jinyoung Choi, Taeyeon Kim, Sangeok Lee, Seokil Son, Minsol Kim, Injung Kim
Bolus segmentation is crucial for the automated detection of swallowing disorders in videofluoroscopic swallowing studies (VFSS).
no code implementations • 20 Mar 2022 • Han Gyel Sun, Hyunjae Ahn, Hyungyu Lee, Injung Kim
In this paper, we propose a new adapter network for adapting a pre-trained deep neural network to a target domain with minimal computation.
no code implementations • 2 Mar 2022 • Sungjae Kim, Yewon Kim, Jewoo Jun, Injung Kim
We propose a multi-singer emotional singing voice synthesizer, Muse-SVS, that expresses emotion at various intensity levels by controlling subtle changes in pitch, energy, and phoneme duration while accurately following the score.
no code implementations • 28 Feb 2022 • JunSeok Oh, Donghwee Yoon, Injung Kim
We propose a one-shot ultra-high-resolution generative adversarial network (OUR-GAN) framework that generates non-repetitive 16K (16, 384 x 8, 640) images from a single training image and is trainable on a single consumer GPU.
no code implementations • 21 Jun 2021 • Minsu Kang, Sungjae Kim, Injung Kim
We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference.
no code implementations • 1 Apr 2021 • Minsu Kang, Jihyun Lee, Simin Kim, Injung Kim
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread.
2 code implementations • 30 Jul 2020 • Jinhyeok Yang, Jun-Mo Lee, Youngik Kim, Hoon-Young Cho, Injung Kim
Additionally, compared with Parallel WaveGAN, another recently developed high-fidelity vocoder, VocGAN is 6. 98x faster on a CPU and exhibits higher MOS.
no code implementations • 31 Jul 2019 • Inyoung Paik, Sangjun Oh, Tae-Yeong Kwak, Injung Kim
To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC).
no code implementations • 31 Jul 2019 • Inyoung Paik, Taeyeong Kwak, Injung Kim
The experimental results show that the routing algorithms do not behave as expected and often produce results that are worse than simple baseline algorithms that assign the connection strengths uniformly or randomly.