5 papers
Exploiting the Prior of Generative Time Series Imputation
YuYang Miao, Chang Li, Zehua Chen
Time series imputation, i.e., filling the missing values of a time recording, finds various applications in electricity, finance, and weather modelling. Previous methods have intro…
Audio Super-Resolution with Latent Bridge Models
Chang Li, Zehua Chen, Liyuan Wang +1
Audio super-resolution (SR), i.e., upsampling the low-resolution (LR) waveform to the high-resolution (HR) version, has recently been explored with diffusion and bridge models, whi…
FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation
Yuxuan Jiang, Zehua Chen, Zeqian Ju +3
Text-to-audio (T2A) generation has achieved promising results with the recent advances in generative models. However, because of the limited quality and quantity of temporally-alig…
Bridge-SR: Schrödinger Bridge for Efficient SR
Chang Li, Zehua Chen, Fan Bao +1
Speech super-resolution (SR), which generates a waveform at a higher sampling rate from its low-resolution version, is a long-standing critical task in speech restoration. Previous…
RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals
Yuyang Miao, Zehua Chen, Chang Li +1
Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) s…