Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection-Reference-Cited by-同舟云学术

Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Braga Otavio¹,Siohan Olivier¹

Affiliation:

1. Google, Inc.

Publisher

IEEE

Link

Reference24 articles.

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Enhancing Robustness in Audio Visual Speech Recognition: A preprocessing approach with Transformer and CTC Loss;2024 International Conference on Advances in Modern Age Technologies for Health and Engineering Science (AMATHE);2024-05-16

2. Large Scale Self-Supervised Pretraining for Active Speaker Detection;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Conformer is All You Need for Visual Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Perceptual Synchronization Scoring of Dubbed Content using Phoneme-Viseme Agreement;2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW);2024-01-01