Search Results for author: Jun-Mo Lee

Found 2 papers, 1 papers with code

VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network

2 code implementations30 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.

Speech Synthesis

Ethanos: Lightweight Bootstrapping for Ethereum

no code implementations14 Nov 2019 Jae-Yun Kim, Jun-Mo Lee, Yeon-Jae Koo, Sang-Hyeon Park, Soo-Mook Moon

Our experimental result shows that ethanos can reduce the size of the account state by half, which, if combined with removing old transactions, may reduce the storage size for bootstrapping to around 1GB.

Cannot find the paper you are looking for? You can Submit a new open access paper.