3 papers
cs.CL2025
Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng +6
Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hid…
cs.SD2025
QR-VC: Leveraging Quantization Residuals for Linear Disentanglement in Zero-Shot Voice Conversion
Youngjun Sim, Jinsung Yoon, Wooyeol Jeong +1
Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring a…
cs.SD2025
Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody
Jinsung Yoon, Wooyeol Jeong, Jio Gim +1
Emotional voice conversion (EVC) aims to modify the emotional style of speech while preserving its linguistic content. In practical EVC, controllability, the ability to independent…