A Brazilian Portuguese Real-Time Voice Recognition to deal with sensitive data

F. Pinna, João Carlos Néto, W. Ruggiero
{"title":"A Brazilian Portuguese Real-Time Voice Recognition to deal with sensitive data","authors":"F. Pinna, João Carlos Néto, W. Ruggiero","doi":"10.1109/IEEECONF44664.2019.9048689","DOIUrl":null,"url":null,"abstract":"Speech recognition is generally performed by a few cloud providers centrally. Such an approach is not suitable for financial and medical institutions because sensitive data cannot be provided openly to third parties. This work proposes a simple chatbot for Brazilian Portuguese real-time speech recognition, well-defined purpose, specific vocabulary, and a secure way without exposing sensitive data for use on mobile devices. The proposed system got a word error rate of 2.38% for a speech recognition task.","PeriodicalId":6684,"journal":{"name":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","volume":"24 1","pages":"1872-1876"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEEECONF44664.2019.9048689","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Speech recognition is generally performed by a few cloud providers centrally. Such an approach is not suitable for financial and medical institutions because sensitive data cannot be provided openly to third parties. This work proposes a simple chatbot for Brazilian Portuguese real-time speech recognition, well-defined purpose, specific vocabulary, and a secure way without exposing sensitive data for use on mobile devices. The proposed system got a word error rate of 2.38% for a speech recognition task.
一个巴西葡萄牙实时语音识别处理敏感数据
语音识别通常由几个云提供商集中执行。这种方法不适合金融和医疗机构,因为敏感数据不能公开提供给第三方。这项工作提出了一个简单的聊天机器人,用于巴西葡萄牙语实时语音识别,明确的目的,特定的词汇表,以及一种不暴露敏感数据的安全方式,用于移动设备。该系统在语音识别任务中的错误率为2.38%。
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