activity
20192022
most citedUnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

4 citations · 4 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2022

Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization

Youngin Cho, Junsoo Lee, Soyoung Yang +6

Existing deep interactive colorization models have focused on ways to utilize various types of interactions, such as point-wise color hints, scribbles, or natural-language texts, a…

cs.SD2022

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

Juntae Kim, Sung Min Ban

The spoof speech detection (SSD) is the essential countermeasure for automatic speaker verification systems. Although SSD with magnitude features in the frequency domain has shown…

eess.AS20214 cited

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

Won Jang, Dan Lim, Jaesam Yoon +2

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acou…

eess.AS2020

Phase-Aware Speech Enhancement with a Recurrent Two Stage Net work

Juntae Kim, Jaesung Bae

We propose a neural network-based speech enhancement (SE) method called the phase-aware recurrent two stage network (rTSN). The rTSN is an extension of our previously proposed two…

eess.AS2019

End-Point Detection with State Transition Model based on Chunk-Wise Classification

Juntae Kim, Jaesung Bae, Minsoo Hahn

A state transition model (STM) based on chunk-wise classification was proposed for end-point detection (EPD). In general, EPD is developed using frame-wise voice activity detection…