Is Lip Region-of-Interest Sufficient for Lipreading?

Lip region-of-interest (ROI) is conventionally used for visual input in the lipreading task. Few works have adopted the entire face as visual input because lip-excluded parts of the face are usually considered to be redundant and irrelevant to visual speech recognition. However, faces contain much m...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jing-Xuan, Zhang, Gen-Shun Wan, Pan, Jia
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 02.06.2022
Subjects
Audio visual equipment
Error reduction
Feature extraction
Lipreading
Speech recognition
Supervised learning
Training
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:Lip region-of-interest (ROI) is conventionally used for visual input in the lipreading task. Few works have adopted the entire face as visual input because lip-excluded parts of the face are usually considered to be redundant and irrelevant to visual speech recognition. However, faces contain much more detailed information than lips, such as speakers' head pose, emotion, identity etc. We argue that such information might benefit visual speech recognition if a powerful feature extractor employing the entire face is trained. In this work, we propose to adopt the entire face for lipreading with self-supervised learning. AV-HuBERT, an audio-visual multi-modal self-supervised learning framework, was adopted in our experiments. Our experimental results showed that adopting the entire face achieved 16% relative word error rate (WER) reduction on the lipreading task, compared with the baseline method using lip as visual input. Without self-supervised pretraining, the model with face input achieved a higher WER than that using lip input in the case of limited training data (30 hours), while a slightly lower WER when using large amount of training data (433 hours).
ISSN:2331-8422