找回密码
 To register

QQ登录

只需一步,快速开始

扫一扫,访问微社区

Titlebook: Data-Driven Techniques in Speech Synthesis; Robert I. Damper Book 2001 Springer Science+Business Media Dordrecht 2001 Intonation.Klang.Pho

[复制链接]
查看: 43637|回复: 50
发表于 2025-3-21 17:44:10 | 显示全部楼层 |阅读模式
书目名称Data-Driven Techniques in Speech Synthesis
编辑Robert I. Damper
视频video
丛书名称Telecommunications Technology & Applications Series
图书封面Titlebook: Data-Driven Techniques in Speech Synthesis;  Robert I. Damper Book 2001 Springer Science+Business Media Dordrecht 2001 Intonation.Klang.Pho
描述.Data-Driven Techniques in Speech Synthesis. gives a firstreview of this new field. All areas of speech synthesis from text arecovered, including text analysis, letter-to-sound conversion, prosodicmarking and extraction of parameters to drive synthesis hardware..Fuelled by cheap computer processing and memory, the fields of machinelearning in particular and artificial intelligence in general areincreasingly exploiting approaches in which large databases act asimplicit knowledge sources, rather than explicit rules manuallywritten by experts. Speech synthesis is one application area where thenew approach is proving powerfully effective, the reliance uponfragile specialist knowledge having hindered its development in thepast. This book provides the first review of the new topic, withcontributions from leading international experts. ..Data-Driven Techniques in Speech Synthesis. is at the leadingedge of current research, written by well respected experts in thefield. The text is concise and accessible, and guides the readerthrough the new technology. The book will primarily appeal to researchengineers and scientists working in the area of speech synthesis.However, it will also be of int
出版日期Book 2001
关键词Intonation; Klang; Phonem; artificial intelligence; communication; corpus; intelligence; learning; machine l
版次1
doihttps://doi.org/10.1007/978-1-4757-3413-3
isbn_softcover978-1-4419-4733-8
isbn_ebook978-1-4757-3413-3
copyrightSpringer Science+Business Media Dordrecht 2001
The information of publication is updating

书目名称Data-Driven Techniques in Speech Synthesis影响因子(影响力)




书目名称Data-Driven Techniques in Speech Synthesis影响因子(影响力)学科排名




书目名称Data-Driven Techniques in Speech Synthesis网络公开度




书目名称Data-Driven Techniques in Speech Synthesis网络公开度学科排名




书目名称Data-Driven Techniques in Speech Synthesis被引频次




书目名称Data-Driven Techniques in Speech Synthesis被引频次学科排名




书目名称Data-Driven Techniques in Speech Synthesis年度引用




书目名称Data-Driven Techniques in Speech Synthesis年度引用学科排名




书目名称Data-Driven Techniques in Speech Synthesis读者反馈




书目名称Data-Driven Techniques in Speech Synthesis读者反馈学科排名




单选投票, 共有 0 人参与投票
 

0票 0%

Perfect with Aesthetics

 

0票 0%

Better Implies Difficulty

 

0票 0%

Good and Satisfactory

 

0票 0%

Adverse Performance

 

0票 0%

Disdainful Garbage

您所在的用户组没有投票权限
发表于 2025-3-21 20:15:08 | 显示全部楼层
发表于 2025-3-22 01:39:05 | 显示全部楼层
发表于 2025-3-22 06:18:00 | 显示全部楼层
Book 2001 analysis, letter-to-sound conversion, prosodicmarking and extraction of parameters to drive synthesis hardware..Fuelled by cheap computer processing and memory, the fields of machinelearning in particular and artificial intelligence in general areincreasingly exploiting approaches in which large da
发表于 2025-3-22 10:40:07 | 显示全部楼层
Heinrich C. Mayr,Willem-Jan van den Heuvelunciation must exactly match the dictionary pronunciation to be correct) on an unseen 1000-word test set. Based on the judgements of three human listeners in a blind assessment study, our system was estimated to have a serious error rate of 16.7% (on whole words) compared to 26.1% for the DECtalk 3.0 rule base.
发表于 2025-3-22 13:54:04 | 显示全部楼层
https://doi.org/10.1007/978-3-031-02195-4ionary — a frequency-tagged corpus — and uses analogy to generate the pronunciation of words not in the dictionary. A range of implementational choices is discussed and the effectiveness of the model for (British) English, German and Māori demonstrated.
发表于 2025-3-22 20:45:35 | 显示全部楼层
https://doi.org/10.1007/978-3-031-02195-4ere, a string of symbols is viewed as a concatenation of independent variable-length subsequences of symbols. The ability of the multigram model to learn relevant subsequences of phonemes is illustrated by the selection of multiphone units for speech synthesis.
发表于 2025-3-22 21:18:59 | 显示全部楼层
发表于 2025-3-23 02:29:43 | 显示全部楼层
Ali Fuad Selvi,Nathanael Rudolphwhich in turn are used to predict accent and phrasing decisions for text-to-speech. Rules generated by these methods achieve more than 95% accuracy for phrasing decisions and 85% for prominence assignment.
发表于 2025-3-23 06:38:22 | 显示全部楼层
 关于派博传思  派博传思旗下网站  友情链接
派博传思介绍 公司地理位置 论文服务流程 影响因子官网 SITEMAP 大讲堂 北京大学 Oxford Uni. Harvard Uni.
发展历史沿革 期刊点评 投稿经验总结 SCIENCEGARD IMPACTFACTOR 派博系数 清华大学 Yale Uni. Stanford Uni.
|Archiver|手机版|小黑屋| 派博传思国际 ( 京公网安备110108008328) GMT+8, 2025-5-7 21:41
Copyright © 2001-2015 派博传思   京公网安备110108008328 版权所有 All rights reserved
快速回复 返回顶部 返回列表