@inproceedings{yang-etal-2024-audiovsr,
title = "{A}udio{VSR}: Enhancing Video Speech Recognition with Audio Data",
author = "Yang, Xiaoda and
Cheng, Xize and
Duan, Jiaqi and
Qiu, Hongshun and
Hong, Minjie and
Fang, Minghui and
Ji, Shengpeng and
Zuo, Jialong and
Hong, Zhiqing and
Zhang, Zhimeng and
Jin, Tao",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.858/",
doi = "10.18653/v1/2024.emnlp-main.858",
pages = "15352--15361",
abstract = "Visual Speech Recognition (VSR) aims to predict spoken content by analyzing lip movements in videos. Recently reported state-of-the-art results in VSR often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are insufficient compared to the audio data. To further enhance the VSR model using the audio data, we employed a generative model for data inflation, integrating the synthetic data with the authentic visual data. Essentially, the generative model incorporates another insight, which enhances the capabilities of the recognition model. For the cross-language issue, previous work has shown poor performance with non-Indo-European languages. We trained a multi-language-family modal fusion model, AudioVSR. Leveraging the concept of modal transfer, we achieved significant results in downstream VSR tasks under conditions of data scarcity. To the best of our knowledge, AudioVSR represents the first work on cross-language-family audio-lip alignment, achieving a new SOTA in the cross-language scenario."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-audiovsr">
<titleInfo>
<title>AudioVSR: Enhancing Video Speech Recognition with Audio Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoda</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xize</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongshun</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjie</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengpeng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialong</namePart>
<namePart type="family">Zuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqing</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhimeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual Speech Recognition (VSR) aims to predict spoken content by analyzing lip movements in videos. Recently reported state-of-the-art results in VSR often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are insufficient compared to the audio data. To further enhance the VSR model using the audio data, we employed a generative model for data inflation, integrating the synthetic data with the authentic visual data. Essentially, the generative model incorporates another insight, which enhances the capabilities of the recognition model. For the cross-language issue, previous work has shown poor performance with non-Indo-European languages. We trained a multi-language-family modal fusion model, AudioVSR. Leveraging the concept of modal transfer, we achieved significant results in downstream VSR tasks under conditions of data scarcity. To the best of our knowledge, AudioVSR represents the first work on cross-language-family audio-lip alignment, achieving a new SOTA in the cross-language scenario.</abstract>
<identifier type="citekey">yang-etal-2024-audiovsr</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.858</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.858/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15352</start>
<end>15361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AudioVSR: Enhancing Video Speech Recognition with Audio Data
%A Yang, Xiaoda
%A Cheng, Xize
%A Duan, Jiaqi
%A Qiu, Hongshun
%A Hong, Minjie
%A Fang, Minghui
%A Ji, Shengpeng
%A Zuo, Jialong
%A Hong, Zhiqing
%A Zhang, Zhimeng
%A Jin, Tao
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F yang-etal-2024-audiovsr
%X Visual Speech Recognition (VSR) aims to predict spoken content by analyzing lip movements in videos. Recently reported state-of-the-art results in VSR often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are insufficient compared to the audio data. To further enhance the VSR model using the audio data, we employed a generative model for data inflation, integrating the synthetic data with the authentic visual data. Essentially, the generative model incorporates another insight, which enhances the capabilities of the recognition model. For the cross-language issue, previous work has shown poor performance with non-Indo-European languages. We trained a multi-language-family modal fusion model, AudioVSR. Leveraging the concept of modal transfer, we achieved significant results in downstream VSR tasks under conditions of data scarcity. To the best of our knowledge, AudioVSR represents the first work on cross-language-family audio-lip alignment, achieving a new SOTA in the cross-language scenario.
%R 10.18653/v1/2024.emnlp-main.858
%U https://aclanthology.org/2024.emnlp-main.858/
%U https://doi.org/10.18653/v1/2024.emnlp-main.858
%P 15352-15361
Markdown (Informal)
[AudioVSR: Enhancing Video Speech Recognition with Audio Data](https://aclanthology.org/2024.emnlp-main.858/) (Yang et al., EMNLP 2024)
ACL
- Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, and Tao Jin. 2024. AudioVSR: Enhancing Video Speech Recognition with Audio Data. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15352–15361, Miami, Florida, USA. Association for Computational Linguistics.