activity
20242026
collaborators

6 papers

cs.CV2026

JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization

Haolun Zheng, Yu He, Tailun Chen +6

Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…

eess.AS2025

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech

Jixun Yao, Yuguang Yang, Yu Pan +5

Integrating human feedback to align text-to-speech (TTS) system outputs with human preferences has proven to be an effective approach for enhancing the robustness of language model…

eess.AS2025

Audiobook-CC: Controllable Long-context Speech Generation for Multicast Audiobook

Min Liu, JingJing Yin, Xiang Zhang +6

Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for…

cs.SD2025

ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speech

Yu Pan, Yanni Hu, Yuguang Yang +5

Despite great advances, achieving high-fidelity emotional voice conversion (EVC) with flexible and interpretable control remains challenging. This paper introduces ClapFM-EVC, a no…

cs.SD2025

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling

Yuguang Yang, Yu Pan, Jixun Yao +6

Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the origina…

eess.AS2024

StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching

Jixun Yao, Yuguang Yang, Yu Pan +4

Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent…