2 papers
cs.SD2023
ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis
Jungil Kong, Junmo Lee, Jeongmin Kim +5
In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker mode…
cs.SD2023
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
Jungil Kong, Jihoon Park, Beomjeong Kim +3
Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has…