9 papers · 1 filter
AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling
Junchuan Zhao, Minh Duc Vu, Bowen Zhang +1
Bandwidth extension (BWE) aims to recover missing high-frequency content from band-limited speech. Existing methods often formulate BWE as a fixed or predefined bandwidth conversio…
Joycent: Multi-Accent TTS via Disentangled Accent Modeling and Layer-Specific Conditioning
Xintong Wang, Junchuan Zhao, Ye Wang
Accent text-to-speech (TTS) aims to synthesize speech with a target accent while preserving speaker identity, but faces two key challenges: disentangling accent from speaker charac…
Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
Leduo Chen, Junchuan Zhao, Shengchen Li
Timbre transfer aims to modify the timbral identity of a musical recording while preserving its original melody and rhythm. While single-instrument timbre transfer has made substan…
CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space
Bowen Zhang, Junchuan Zhao, Ian McLoughlin +2
Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech. Existing methods often rely on s…
MSpoofTTS: Multi-Resolution Spoof-Guided Inference for Discrete Speech Synthesis
Junchuan Zhao, Minh Duc Vu, Ye Wang
Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade pe…
TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis
Qifan Liang, Yuansen Liu, Ruixin Wei +3
While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance ex…
Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription
Wei Zeng, Junchuan Zhao, Ye Wang
Expressive performance rendering (EPR) and automatic piano transcription (APT) are fundamental yet inverse tasks in music information retrieval: EPR generates expressive performanc…
CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance
Junchuan Zhao, Wei Zeng, Tianle Lyu +1
Singing Voice Synthesis (SVS) aims to generate expressive vocal performances from structured musical inputs such as lyrics and pitch sequences. While recent progress in discrete co…
Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning
Junchuan Zhao, Xintong Wang, Ye Wang
Recent advances in discrete audio codecs have significantly improved speech representation modeling, while codec language models have enabled in-context learning for zero-shot spee…