3 papers
cs.SD2025
Bridging the gap between training and inference in LM-based TTS models
Ruonan Zhang, Lingzhou Mu, Xixin Wu +1
Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training…
cs.SD2025
MBCodec:Thorough disentangle for high-fidelity audio compression
Ruonan Zhang, Xiaoyang Hao, Yichen Han +3
High-fidelity neural audio codecs in Text-to-speech (TTS) aim to compress speech signals into discrete representations for faithful reconstruction. However, prior approaches faced…
cs.CV2025
FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework
Lingzhou Mu, Qiang Wang, Fan Jiang +4
Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level task…