Junchuan Zhao

11 papers A 1Misc 1Journal 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space.
CoRR
Bowen Zhang, Junchuan Zhao, Ian McLoughlin, Ye Wang, A. S. Madhukumar
2026 J jnl
Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection.
CoRR
Junchuan Zhao, Minh Duc Vu, Ye Wang
2026 J jnl
Segment-Aware Conditioning for Training-Free Intra-Utterance Emotion and Duration Control in Text-to-Speech.
CoRR
Qifan Liang, Yuansen Liu, Ruixin Wei, Nan Lu, Junchuan Zhao, Ye Wang
2025 J jnl
CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance.
CoRR
Junchuan Zhao, Wei Zeng, Tianle Lyu, Ye Wang
2025 J jnl
Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription.
CoRR
Wei Zeng, Junchuan Zhao, Ye Wang
2025 J jnl
InconVAD: A Two-Stage Dual-Tower Framework for Multimodal Emotion Inconsistency Detection.
CoRR
Zongyi Li, Junchuan Zhao, Francis Bu Sung Lee, Andrew Zi Han Yee
2025 J jnl
KSDiff: Keyframe-Augmented Speech-Aware Dual-Path Diffusion for Facial Animation.
CoRR
Tianle Lyu, Junchuan Zhao, Ye Wang
2025 A conf
Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning.
INTERSPEECH
Junchuan Zhao, Xintong Wang, Ye Wang
2025 J jnl
Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning.
CoRR
Junchuan Zhao, Xintong Wang, Ye Wang
2025 Misc conf
SPSinger: Multi-Singer Singing Voice Synthesis with Short Reference Prompt.
ICASSP
Junchuan Zhao, Chetwin Low, Ye Wang
2024 J jnl
SinTechSVS: A Singing Technique Controllable Singing Voice Synthesis System.
IEEE ACM Trans. Audio Speech Lang. Process.
Junchuan Zhao, Low Qi Hong Chetwin, Ye Wang