1 citations · 1 across the 6 of their papers we have counts for
5 papers · 1 filter
Mitigating Latent Mismatch in cVAE-Based Singing Voice Synthesis via Flow Matching
Minhyeok Yun, Yong-Hoon Choi
Singing voice synthesis (SVS) aims to generate natural and expressive singing waveforms from symbolic musical scores. In cVAE-based SVS, however, a mismatch arises because the deco…
Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions
Euiyeon Kim, Yong-Hoon Choi
We introduce a new music source separation model tailored for accurate vocal isolation. Unlike Transformer-based approaches, which often fail to capture intermittently occurring vo…
RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer
Seongho Hong, Yong-Hoon Choi
While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation…
Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
Myeongjin Ko, Yong-Hoon Choi
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requireme…
SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer
Daegyeom Kim, Seongho Hong, Yong-Hoon Choi
Expressive speech synthesis models are trained by adding corpora with diverse speakers, various emotions, and different speaking styles to the dataset, in order to control various…