EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech
Paper • 2406.07803 • Published
Hyungseok Oh
hsoh
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector authored a paper 1 day ago
HierVST: Hierarchical Adaptive Zero-shot Voice Style TransferOrganizations
None yet
authored 5
papers 1 day ago
EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector
Paper • 2411.02625 • Published
HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer
Paper • 2307.16171 • Published
DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
Paper • 2505.19687 • Published
JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech Synthesis
Paper • 2501.04904 • Published
authored 3
papers 2 days ago
Toward Complex-Valued Neural Networks for Waveform Generation
Paper • 2603.11589 • Published
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment
Paper • 2401.08095 • Published
DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
Paper • 2307.16549 • Published
updated a
model 6 days ago
published a
model 6 days ago