Papers
arxiv:2404.05466

Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder

Published on Apr 8, 2024
Authors:
,
,
,

Abstract

A proposed multi-scale and multi-encoder approach enhances automatic lip-reading by incorporating Branchformer and E-Branchformer, achieving significant improvement in character error rate.

AI-generated summary

Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single scale. In this paper, we propose to enhance lip-reading by incorporating multi-scale video data and multi-encoder. Specifically, we first propose a novel multi-scale lip motion extraction algorithm based on the size of the speaker's face and an Enhanced ResNet3D visual front-end (VFE) to extract lip features at different scales. For the multi-encoder, in addition to the mainstream Transformer and Conformer, we also incorporate the recently proposed Branchformer and E-Branchformer as visual encoders. In the experiments, we explore the influence of different video data scales and encoders on ALR system performance and fuse the texts transcribed by all ALR systems using recognizer output voting error reduction (ROVER). Finally, our proposed approach placed second in the ICME 2024 ChatCLR Challenge Task 2, with a 21.52% reduction in character error rate (CER) compared to the official baseline on the evaluation set.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2404.05466 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2404.05466 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2404.05466 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.