1 code implementation • 4 Oct 2023 • Sangjun Park, JinYeong Bak
Transformer-based models still face the structural limitation of fixed context length in processing long sequence input despite their effectiveness in various fields.
no code implementations • 4 Apr 2022 • JIhwan Lee, Joun Yeop Lee, Heejin Choi, Seongkyu Mun, Sangjun Park, Jae-Sung Bae, Chanwoo Kim
Two proposed modules are added to the end-to-end TTS framework: an intonation predictor and an intonation encoder.
no code implementations • 27 Mar 2022 • Sangjun Park, Kihyun Choo, Joohyung Lee, Anton V. Porov, Konstantin Osipov, June Sig Sung
Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e. g., latency and privacy issues.
1 code implementation • 26 Jan 2021 • Hyoungsung Kim, Jehyuk Jang, Sangjun Park, Heung-No Lee
A finite mean block generation time (BGT) and none heavy-tail BGT distribution are the ones of the focus in this study.
Cryptography and Security
no code implementations • 11 Aug 2020 • Ravichander Vipperla, Sangjun Park, Kihyun Choo, Samin Ishtiaq, Kyoungbo Min, Sourav Bhattacharya, Abhinav Mehrotra, Alberto Gil C. P. Ramos, Nicholas D. Lane
LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low.