Papers
arxiv:2505.04394

SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer

Published on May 7, 2025
Authors:
,

Abstract

A lightweight visual speech encoder based on Swin Transformer architecture improves lip reading performance and efficiency compared to traditional CNN approaches.

This paper presents an efficient visual speech encoder for lip reading. While most recent lip reading studies have been based on the ResNet architecture and have achieved significant success, they are not sufficiently suitable for efficiently capturing lip reading features due to high computational complexity in modeling spatio-temporal information. Additionally, using a complex visual model not only increases the complexity of lip reading models but also induces delays in the overall network for multi-modal studies (e.g., audio-visual speech recognition, speech enhancement, and speech separation). To overcome the limitations of Convolutional Neural Network (CNN)-based models, we apply the hierarchical structure and window self-attention of the Swin Transformer to lip reading. We configure a new lightweight scale of the Swin Transformer suitable for processing lip reading data and present the SwinLip visual speech encoder, which efficiently reduces computational load by integrating modified Convolution-augmented Transformer (Conformer) temporal embeddings with conventional spatial embeddings in the hierarchical structure. Through extensive experiments, we have validated that our SwinLip successfully improves the performance and inference speed of the lip reading network when applied to various backbones for word and sentence recognition, reducing computational load. In particular, our SwinLip demonstrated robust performance in both English LRW and Mandarin LRW-1000 datasets and achieved state-of-the-art performance on the Mandarin LRW-1000 dataset with less computation compared to the existing state-of-the-art model.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2505.04394
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2505.04394 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/2505.04394 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/2505.04394 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.