4 papers
RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
Jinhyeok Yang, Hyeongju Kim, Yechan Yu +3
While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repe…
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Lucheng Fu, Ye Yu, Yiyang Wang +4
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rew…
Training Flow Matching Models with Reliable Labels via Self-Purification
Hyeongju Kim, Yechan Yu, June Young Yi +1
Training datasets are inherently imperfect, often containing mislabeled samples due to human annotation errors, limitations of tagging models, and other sources of noise. Such labe…
SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System
Hyeongju Kim, Jinhyeok Yang, Yechan Yu +5
We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoenco…