A Review on Shouted Speech Detection Technique

Ch. Vyshnavi, B. Vasavi, M. Bhavana, Nookala Sai Homitha, Suneetha Bulla
{"title":"A Review on Shouted Speech Detection Technique","authors":"Ch. Vyshnavi, B. Vasavi, M. Bhavana, Nookala Sai Homitha, Suneetha Bulla","doi":"10.1109/ICSMDI57622.2023.00026","DOIUrl":null,"url":null,"abstract":"The primary cause of competitive speech in TV news debates is disagreement among panel members. In competitive situations, panel members frequently interrupt the active speaker to emphasize their point of view. In most cases, neither the active speaker nor the interrupters stop speaking. As a result, extended periods of continuous speech overlap occur. Speaker conflicts are unpleasant for the active speaker and can provoke aggressive responses. In most cases, induced aggression manifests as shouted speech. As a result, the presence of shouted and overlapped speech in TV news debates may be regarded as critical cues for detecting competitive speech. As a result, an in-depth understanding of the acoustics of shouted and overlapped speech is required. Previous speech researchers attempted to understand various aspects of shouted, overlapping, and competitive speech as separate tasks. The current thesis was motivated by the limitations of the available literature.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSMDI57622.2023.00026","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The primary cause of competitive speech in TV news debates is disagreement among panel members. In competitive situations, panel members frequently interrupt the active speaker to emphasize their point of view. In most cases, neither the active speaker nor the interrupters stop speaking. As a result, extended periods of continuous speech overlap occur. Speaker conflicts are unpleasant for the active speaker and can provoke aggressive responses. In most cases, induced aggression manifests as shouted speech. As a result, the presence of shouted and overlapped speech in TV news debates may be regarded as critical cues for detecting competitive speech. As a result, an in-depth understanding of the acoustics of shouted and overlapped speech is required. Previous speech researchers attempted to understand various aspects of shouted, overlapping, and competitive speech as separate tasks. The current thesis was motivated by the limitations of the available literature.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
大声语音检测技术综述
电视新闻辩论中竞争性言论的主要原因是小组成员之间的分歧。在竞争激烈的情况下,小组成员经常打断正在发言的人来强调他们的观点。在大多数情况下,主动说话者和打断者都不会停止说话。结果,出现了长时间的连续语言重叠。说话者之间的冲突对主动说话者来说是不愉快的,并可能引发攻击性的反应。在大多数情况下,诱发性攻击表现为大声说话。因此,电视新闻辩论中出现的大声喊叫和重叠的言语可能被视为检测竞争性言语的关键线索。因此,需要深入了解喊叫和重叠语音的声学。以前的语言研究人员试图将喊叫、重叠和竞争性语言的各个方面作为单独的任务来理解。当前这篇论文的动机是现有文献的局限性。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Decentralized Flight Insurance Smart Contract Application using Blockchain Stock Market Prediction using Machine Learning Technique HarGharSolar : Recognition of Potential Rooftop PhotoVoltaic Arrays Using Geospatial Imagery for Diverse Climate Zones. Artificial Intelligence Powered Early Detection of Heart Disease Network Intrusion Detection using Machine Learning Algorithms
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1