Alert button
Picture for Jing-Xuan Zhang

Jing-Xuan Zhang

Alert button

Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation

Dec 06, 2022
Jing-Xuan Zhang, Genshun Wan, Zhen-Hua Ling, Jia Pan, Jianqing Gao, Cong Liu

Figure 1 for Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
Figure 2 for Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
Figure 3 for Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
Figure 4 for Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
Viaarxiv icon

Is Lip Region-of-Interest Sufficient for Lipreading?

Jun 02, 2022
Jing-Xuan Zhang, Gen-Shun Wan, Jia Pan

Figure 1 for Is Lip Region-of-Interest Sufficient for Lipreading?
Figure 2 for Is Lip Region-of-Interest Sufficient for Lipreading?
Figure 3 for Is Lip Region-of-Interest Sufficient for Lipreading?
Figure 4 for Is Lip Region-of-Interest Sufficient for Lipreading?
Viaarxiv icon

TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos

Nov 19, 2020
Manuel Sam Ribeiro, Jennifer Sanger, Jing-Xuan Zhang, Aciel Eshky, Alan Wrench, Korin Richmond, Steve Renals

Figure 1 for TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos
Figure 2 for TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos
Figure 3 for TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos
Figure 4 for TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos
Viaarxiv icon

Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis

Jul 18, 2018
Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai

Figure 1 for Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
Figure 2 for Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
Figure 3 for Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
Figure 4 for Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
Viaarxiv icon