Picture for Seunghun Ji

Seunghun Ji

SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System

Add code
Mar 29, 2025
Viaarxiv icon

DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance

Add code
Aug 27, 2024
Figure 1 for DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
Figure 2 for DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
Figure 3 for DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
Viaarxiv icon