F-5-TTS

The 'F-5-TTS' dataset/benchmark is used to evaluate text-to-speech systems, specifically in terms of their performance in cross-lingual voice cloning and audio quality.

Papers using F-5-TTS (5)

Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS2026FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion2026DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration2025Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis2025