Alert button
Picture for Zheng-Hua Tan

Zheng-Hua Tan

Alert button

Aalborg University, Pioneer Centre for AI, Denmark

Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions

Dec 27, 2023
Holger Severin Bovbjerg, Jesper Jensen, Jan Østergaard, Zheng-Hua Tan

Viaarxiv icon

PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNs

Dec 15, 2023
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky

Viaarxiv icon

Investigating the Design Space of Diffusion Models for Speech Enhancement

Dec 07, 2023
Philippe Gonzalez, Zheng-Hua Tan, Jan Østergaard, Jesper Jensen, Tommy Sonne Alstrøm, Tobias May

Viaarxiv icon

Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler

Dec 05, 2023
Philippe Gonzalez, Zheng-Hua Tan, Jan Østergaard, Jesper Jensen, Tommy Sonne Alstrøm, Tobias May

Viaarxiv icon

Joint Minimum Processing Beamforming and Near-end Listening Enhancement

Sep 20, 2023
Andreas J. Fuglsig, Jesper Jensen, Zheng-Hua Tan, Lars S. Bertelsen, Jens Christian Lindof, Jan Østergaard

Viaarxiv icon

Masked Autoencoders with Multi-Window Attention Are Better Audio Learners

Jun 01, 2023
Sarthak Yadav, Sergios Theodoridis, Lars Kai Hansen, Zheng-Hua Tan

Figure 1 for Masked Autoencoders with Multi-Window Attention Are Better Audio Learners
Figure 2 for Masked Autoencoders with Multi-Window Attention Are Better Audio Learners
Figure 3 for Masked Autoencoders with Multi-Window Attention Are Better Audio Learners
Figure 4 for Masked Autoencoders with Multi-Window Attention Are Better Audio Learners
Viaarxiv icon

Speech inpainting: Context-based speech synthesis guided by video

Jun 01, 2023
Juan F. Montesinos, Daniel Michelsanti, Gloria Haro, Zheng-Hua Tan, Jesper Jensen

Figure 1 for Speech inpainting: Context-based speech synthesis guided by video
Figure 2 for Speech inpainting: Context-based speech synthesis guided by video
Figure 3 for Speech inpainting: Context-based speech synthesis guided by video
Figure 4 for Speech inpainting: Context-based speech synthesis guided by video
Viaarxiv icon

PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss

Mar 29, 2023
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafael Wisniewski, Mihaly Petreczky

Figure 1 for PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss
Viaarxiv icon

PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models

Dec 30, 2022
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky

Figure 1 for PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Figure 2 for PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Figure 3 for PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Figure 4 for PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Viaarxiv icon

Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise

Nov 19, 2022
Iván López-Espejo, Ram C. M. C. Shekar, Zheng-Hua Tan, Jesper Jensen, John H. L. Hansen

Figure 1 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 2 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 3 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 4 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Viaarxiv icon