Saved in:
Bibliographic Details
Main Authors: Dai, Yusheng, Chen, Hang, Du, Jun, Ding, Xiaofei, Ding, Ning, Jiang, Feijun, Lee, Chin-Hui
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.08488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910360077860864
author Dai, Yusheng
Chen, Hang
Du, Jun
Ding, Xiaofei
Ding, Ning
Jiang, Feijun
Lee, Chin-Hui
author_facet Dai, Yusheng
Chen, Hang
Du, Jun
Ding, Xiaofei
Ding, Ning
Jiang, Feijun
Lee, Chin-Hui
contents In recent research, slight performance improvement is observed from automatic speech recognition systems to audio-visual speech recognition systems in the end-to-end framework with low-quality videos. Unmatching convergence rates and specialized input representations between audio and visual modalities are considered to cause the problem. In this paper, we propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. This enables accurate alignment of video and audio streams during visual model pre-training and cross-modal fusion. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers to make full use of modality complementarity. Experiments on the MISP2021-AVSR data set show the effectiveness of the two proposed techniques. Together, using only a relatively small amount of training data, the final system achieves better performances than state-of-the-art systems with more complex front-ends and back-ends.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08488
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
Dai, Yusheng
Chen, Hang
Du, Jun
Ding, Xiaofei
Ding, Ning
Jiang, Feijun
Lee, Chin-Hui
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
In recent research, slight performance improvement is observed from automatic speech recognition systems to audio-visual speech recognition systems in the end-to-end framework with low-quality videos. Unmatching convergence rates and specialized input representations between audio and visual modalities are considered to cause the problem. In this paper, we propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. This enables accurate alignment of video and audio streams during visual model pre-training and cross-modal fusion. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers to make full use of modality complementarity. Experiments on the MISP2021-AVSR data set show the effectiveness of the two proposed techniques. Together, using only a relatively small amount of training data, the final system achieves better performances than state-of-the-art systems with more complex front-ends and back-ends.
title Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2308.08488