用于视听语音识别的递归神经网络换能器

Takaki Makino, H. Liao, Yannis Assael, Brendan Shillingford, Basi García, Otavio Braga, O. Siohan
{"title":"用于视听语音识别的递归神经网络换能器","authors":"Takaki Makino, H. Liao, Yannis Assael, Brendan Shillingford, Basi García, Otavio Braga, O. Siohan","doi":"10.1109/ASRU46091.2019.9004036","DOIUrl":null,"url":null,"abstract":"This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of segmented utterances extracted from YouTube public videos, leading to 31k hours of audio-visual training content. The performance of an audio-only, visual-only, and audio-visual system are compared on two large-vocabulary test sets: a set of utterance segments from public YouTube videos called YTDEV18 and the publicly available LRS3-TED set. To highlight the contribution of the visual modality, we also evaluated the performance of our system on the YTDEV18 set artificially corrupted with background noise and overlapping speech. To the best of our knowledge, our system significantly improves the state-of-the-art on the LRS3-TED set.","PeriodicalId":150913,"journal":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"96","resultStr":"{\"title\":\"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition\",\"authors\":\"Takaki Makino, H. Liao, Yannis Assael, Brendan Shillingford, Basi García, Otavio Braga, O. Siohan\",\"doi\":\"10.1109/ASRU46091.2019.9004036\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of segmented utterances extracted from YouTube public videos, leading to 31k hours of audio-visual training content. The performance of an audio-only, visual-only, and audio-visual system are compared on two large-vocabulary test sets: a set of utterance segments from public YouTube videos called YTDEV18 and the publicly available LRS3-TED set. To highlight the contribution of the visual modality, we also evaluated the performance of our system on the YTDEV18 set artificially corrupted with background noise and overlapping speech. To the best of our knowledge, our system significantly improves the state-of-the-art on the LRS3-TED set.\",\"PeriodicalId\":150913,\"journal\":{\"name\":\"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"volume\":\"186 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"96\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASRU46091.2019.9004036\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU46091.2019.9004036","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 96

摘要

本文提出了一种基于递归神经网络换能器(RNN-T)架构的大规模视听语音识别系统。为了支持这样一个系统的开发,我们建立了一个大型的视听(a /V)数据集,这些数据集是从YouTube公共视频中提取的分段话语,从而产生了31k小时的视听培训内容。在两个大词汇量的测试集上比较了纯音频、纯视觉和视听系统的性能:一组来自YouTube公共视频YTDEV18的话语片段和公开可用的LRS3-TED集。为了突出视觉模态的贡献,我们还评估了我们的系统在被背景噪声和重叠语音人为破坏的YTDEV18设置上的性能。据我们所知,我们的系统显著提高了LRS3-TED集的技术水平。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of segmented utterances extracted from YouTube public videos, leading to 31k hours of audio-visual training content. The performance of an audio-only, visual-only, and audio-visual system are compared on two large-vocabulary test sets: a set of utterance segments from public YouTube videos called YTDEV18 and the publicly available LRS3-TED set. To highlight the contribution of the visual modality, we also evaluated the performance of our system on the YTDEV18 set artificially corrupted with background noise and overlapping speech. To the best of our knowledge, our system significantly improves the state-of-the-art on the LRS3-TED set.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:604180095
Book学术官方微信