VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
Jungil Kong, Jihoon Park, Beomjeong Kim, Jeongmin Kim, Dohee Kong, Sangjin Kim
Topics & Concepts
Adversarial systemComputer scienceQuality (philosophy)ArchitectureSpeech recognitionArtificial intelligenceStage (stratigraphy)Natural language processingPhilosophyPaleontologyBiologyArtEpistemologyVisual artsSpeech Recognition and SynthesisSpeech and Audio ProcessingSpeech and dialogue systems