Speech recognition issues for directory assistance applications

C. Kamm, C. Shamieh, S. Singhal
{"title":"Speech recognition issues for directory assistance applications","authors":"C. Kamm, C. Shamieh, S. Singhal","doi":"10.1109/IVTTA.1994.341552","DOIUrl":null,"url":null,"abstract":"Telephone companies in the United States handle over 6 billion directory assistance (DA) calls each year. Automation of even a portion of DA calls could significantly reduce the cost of DA services. The paper explores two factors affecting successful automation of DA: a) the effect of directory size on speech recognition performance, and b) the complexity of existing DA call interactions. Speech recognition performance for a set of 200 spoken names was measured for directories ranging from 200 to 1.5 million unique names. Recognition accuracy decreased from 82.5 percent for a 200-name directory to 18.5 percent for a 1.5 million name directory. In part because high recognition accuracy is not easily achievable for these very large, low-context directories, it is likely that initial implementations of DA automation will focus on a small percentage of calls, requiring a smaller vocabulary. To maximize the potential savings, listings that are most frequently requested appear to be the optimal vocabulary. To identify critical issues in automating frequent DA requests, approximately 13,000 DA calls from an office near a major metropolitan area in the United States were studied. In this sample, 245 listings covered 10 percent of the call volume, and 870 listings covered 20 percent of the call volume.<<ETX>>","PeriodicalId":435907,"journal":{"name":"Proceedings of 2nd IEEE Workshop on Interactive Voice Technology for Telecommunications Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"43","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of 2nd IEEE Workshop on Interactive Voice Technology for Telecommunications Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVTTA.1994.341552","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 43

Abstract

Telephone companies in the United States handle over 6 billion directory assistance (DA) calls each year. Automation of even a portion of DA calls could significantly reduce the cost of DA services. The paper explores two factors affecting successful automation of DA: a) the effect of directory size on speech recognition performance, and b) the complexity of existing DA call interactions. Speech recognition performance for a set of 200 spoken names was measured for directories ranging from 200 to 1.5 million unique names. Recognition accuracy decreased from 82.5 percent for a 200-name directory to 18.5 percent for a 1.5 million name directory. In part because high recognition accuracy is not easily achievable for these very large, low-context directories, it is likely that initial implementations of DA automation will focus on a small percentage of calls, requiring a smaller vocabulary. To maximize the potential savings, listings that are most frequently requested appear to be the optimal vocabulary. To identify critical issues in automating frequent DA requests, approximately 13,000 DA calls from an office near a major metropolitan area in the United States were studied. In this sample, 245 listings covered 10 percent of the call volume, and 870 listings covered 20 percent of the call volume.<>
目录协助应用程序的语音识别问题
美国的电话公司每年要处理超过60亿的目录查询(DA)电话。即使是部分数据处理调用的自动化也可以显著降低数据处理服务的成本。本文探讨了影响自动数据挖掘成功自动化的两个因素:a)目录大小对语音识别性能的影响;b)现有自动数据挖掘调用交互的复杂性。在200到150万个不同名字的目录中,对一组200个名字的语音识别性能进行了测试。识别准确率从200个名称目录的82.5%下降到150万个名称目录的18.5%。部分原因是对于这些非常大的、低上下文的目录不容易实现高识别精度,因此数据处理自动化的初始实现很可能只关注一小部分调用,需要更小的词汇表。为了最大化潜在的节省,最常被请求的清单似乎是最佳的词汇表。为了确定频繁的数据处理请求自动化中的关键问题,研究了来自美国一个主要大都市附近的一个办公室的大约13,000个数据处理呼叫。在这个示例中,245个列表覆盖了10%的呼叫量,870个列表覆盖了20%的呼叫量。
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