21 citations · 45 across the 8 of their papers we have counts for
8 papers
Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networks
Han Gyel Sun, Hyunjae Ahn, HyunGyu Lee +1
In this paper, we propose a new adapter network for adapting a pre-trained deep neural network to a target domain with minimal computation. The proposed model, unidirectional thin…
MuSE-SVS: Multi-Singer Emotional Singing Voice Synthesizer that Controls Emotional Intensity
Sungjae Kim, Yewon Kim, Jewoo Jun +1
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 phon…
One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPU
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 im…
UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control
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. UniTTS represents multiple…
Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
Minsu Kang, Jihyun Lee, Simin Kim +1
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweigh…
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network
Jinhyeok Yang, Junmo Lee, Youngik Kim +2
We present a novel high-fidelity real-time neural vocoder called VocGAN. A recently developed GAN-based vocoder, MelGAN, produces speech waveforms in real-time. However, it often p…
Capsule Networks Need an Improved Routing Algorithm
Inyoung Paik, Taeyeong Kwak, Injung Kim
In capsule networks, the routing algorithm connects capsules in consecutive layers, enabling the upper-level capsules to learn higher-level concepts by combining the concepts of th…
Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control
Inyoung Paik, Sangjun Oh, Tae-Yeong Kwak +1
To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning…