most citedCross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition

2 citations · 7 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

Text-based Talking Video Editing with Cascaded Conditional Diffusion

Bo Han, Heqing Zou, Haoyang Li +2

Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging…

cs.MM20241 cited

Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection

Heqing Zou, Meng Shen, Yuchen Hu +3

Audio-visual deepfake detection scrutinizes manipulations in public video using complementary multimodal cues. Current methods, which train on fused multimodal data for multimodal…

cs.CV20231 cited

UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning

Heqing Zou, Meng Shen, Chen Chen +3

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based…

eess.AS20232 cited

Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition

Yuchen Hu, Ruizhe Li, Chen Chen +3

Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-in…

cs.SD20232 cited

Unsupervised Noise adaptation using Data Simulation

Chen Chen, Yuchen Hu, Heqing Zou +2

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformati…

eess.AS20231 cited

Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation

Yuchen Hu, Chen Chen, Heqing Zou +2

Recent studies in neural network-based monaural speech separation (SS) have achieved a remarkable success thanks to increasing ability of long sequence modeling. However, they woul…