CASIA OpenIR  > 模式识别国家重点实验室  > 智能交互
基于内容和声学特征层级融合的自动韵律边界标注
傅睿博; 陶建华; 温正棋
Source Publication中国语音学报
2018-10
Issue10Pages:103-110
Subtype期刊
Abstract

韵律边界标注对于语料库建设和语音合成有着至关重要的作用,而自动韵律标注可以克服人工标注中不一致、耗时的缺点。仿照人工标注流程,本文对文本特征和声学特征采用层级融合的方式运用循环神经网络训练自动韵律边界标注模型。本文以词为单位提取了静音时长,与传统以帧为单位的声学特征相比更具有明确的物理意义,与韵律边界的联系更加紧密。实验结果表明,相比于传统声学特征,本文所采用的静音时长特征使自动韵律标注的性能有所提高;相比于直接特征层面融合和决策层融合的方法,特征层级融合方法更好地结合了声学和文本的特征,进一步提高了标注的性能。

Keyword韵律边界标注 特征层级融合 语料库构建 语音合成
Indexed ByEI
Language中文
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39601
Collection模式识别国家重点实验室_智能交互
Corresponding Author傅睿博
Affiliation中国科学院自动化研究所
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
傅睿博,陶建华,温正棋. 基于内容和声学特征层级融合的自动韵律边界标注[J]. 中国语音学报,2018(10):103-110.
APA 傅睿博,陶建华,&温正棋.(2018).基于内容和声学特征层级融合的自动韵律边界标注.中国语音学报(10),103-110.
MLA 傅睿博,et al."基于内容和声学特征层级融合的自动韵律边界标注".中国语音学报 .10(2018):103-110.
Files in This Item: Download All
File Name/Size DocType Version Access License
中国语音学报(期刊).pdf(1209KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[傅睿博]'s Articles
[陶建华]'s Articles
[温正棋]'s Articles
Baidu academic
Similar articles in Baidu academic
[傅睿博]'s Articles
[陶建华]'s Articles
[温正棋]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[傅睿博]'s Articles
[陶建华]'s Articles
[温正棋]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 中国语音学报(期刊).pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.