Multimodal embedding fusion for robust speaker role recognition in video broadcast

Mickael Rouvier, Sebastien Delecraz, Benoit Favre, Meriem Bendris, Frédéric Béchet
{"title":"Multimodal embedding fusion for robust speaker role recognition in video broadcast","authors":"Mickael Rouvier, Sebastien Delecraz, Benoit Favre, Meriem Bendris, Frédéric Béchet","doi":"10.1109/ASRU.2015.7404820","DOIUrl":null,"url":null,"abstract":"Person role recognition in video broadcasts consists in classifying people into roles such as anchor, journalist, guest, etc. Existing approaches mostly consider one modality, either audio (speaker role recognition) or image (shot role recognition), firstly because of the non-synchrony between both modalities, and secondly because of the lack of a video corpus annotated in both modalities. Deep Neural Networks (DNN) approaches offer the ability to learn simultaneously feature representations (embeddings) and classification functions. This paper presents a multimodal fusion of audio, text and image embeddings spaces for speaker role recognition in asynchronous data. Monomodal embeddings are trained on exogenous data and fine-tuned using a DNN on 70 hours of French Broadcasts corpus for the target task. Experiments on the REPERE corpus show the benefit of the embeddings level fusion compared to the monomodal embeddings systems and to the standard late fusion method.","PeriodicalId":89617,"journal":{"name":"Proceedings. IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"62 1","pages":"383-389"},"PeriodicalIF":0.0000,"publicationDate":"2015-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. IEEE Workshop on Automatic Speech Recognition and Understanding","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2015.7404820","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Person role recognition in video broadcasts consists in classifying people into roles such as anchor, journalist, guest, etc. Existing approaches mostly consider one modality, either audio (speaker role recognition) or image (shot role recognition), firstly because of the non-synchrony between both modalities, and secondly because of the lack of a video corpus annotated in both modalities. Deep Neural Networks (DNN) approaches offer the ability to learn simultaneously feature representations (embeddings) and classification functions. This paper presents a multimodal fusion of audio, text and image embeddings spaces for speaker role recognition in asynchronous data. Monomodal embeddings are trained on exogenous data and fine-tuned using a DNN on 70 hours of French Broadcasts corpus for the target task. Experiments on the REPERE corpus show the benefit of the embeddings level fusion compared to the monomodal embeddings systems and to the standard late fusion method.
视频广播中多模态嵌入融合的鲁棒说话人角色识别
视频直播中的人物角色识别包括将人物划分为主播、记者、嘉宾等角色。现有的方法大多只考虑一种模态,要么是音频(说话人角色识别),要么是图像(镜头角色识别),首先是因为两种模态之间不同步,其次是因为缺乏两种模态注释的视频语料库。深度神经网络(DNN)方法提供了同时学习特征表示(嵌入)和分类函数的能力。本文提出了一种多模态融合音频、文本和图像嵌入空间的方法,用于异步数据中的说话人角色识别。单模嵌入在外源数据上进行训练,并在目标任务的70小时法语广播语料库上使用DNN进行微调。在REPERE语料库上的实验表明,与单模嵌入系统和标准的后期融合方法相比,嵌入水平融合具有明显的优越性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信