CASIA OpenIR  > 09年以前成果
Prosody conversion from neutral speech to emotional speech
Tao, JH; Kang, YG; Li, AJ
2006-07-01
发表期刊IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
卷号14期号:4页码:1145-1154
文章类型Article
摘要Emotion is an important element in expressive speech synthesis. Unlike traditional discrete emotion simulations, this 5 paper attempts to synthesize emotional speech by using "strong" "medium," and "weak" classifications. This paper tests different models, a linear modification model (LMM), a Gaussian mixture model (GMM), and a classification and regression tree (CART) model. The linear modification model makes direct modification of sentence F0 contours and syllabic durations from acoustic distributions of emotional speech, such as, F0 topline, F0 baseline, durations, and intensities. Further analysis shows that emotional speech is also related to stress and linguistic information. Unlike the linear modification method, the GMM and CART models try to map the subtle prosody distributions between neutral and emotional speech. While the GMM just uses the features, the CART model integrates linguistic features into the mapping. A pitch target model which is optimized to describe Mandarin F0 contours is also introduced. For all conversion methods, a deviation of perceived expressiveness (DPE) measure is created to evaluate the expressiveness of the output speech., The results show that the LMM gives the worst results among the three methods. The GMM method is more suitable for a small training set, while the CART method gives the better emotional speech output if trained With a large context-balanced corpus. The methods discussed in this paper indicate ways to generate emotional speech in speech synthesis. The objective and subjective evaluation processes are also analyzed. These results support the use of a neutral semantic content text in databases for emotional speech synthesis.
关键词Emotional Speech Prosody Analysis Speech Synthesis
WOS标题词Science & Technology ; Technology
关键词[WOS]VOICE CONVERSION
收录类别SCI
语种英语
WOS研究方向Acoustics ; Engineering
WOS类目Acoustics ; Engineering, Electrical & Electronic
WOS记录号WOS:000238709200007
引用统计
被引频次:92[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/9283
专题09年以前成果
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
2.Chinese Acad Social Sci, Inst Linguist, Beijing 100732, Peoples R China
推荐引用方式
GB/T 7714
Tao, JH,Kang, YG,Li, AJ. Prosody conversion from neutral speech to emotional speech[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2006,14(4):1145-1154.
APA Tao, JH,Kang, YG,&Li, AJ.(2006).Prosody conversion from neutral speech to emotional speech.IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,14(4),1145-1154.
MLA Tao, JH,et al."Prosody conversion from neutral speech to emotional speech".IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 14.4(2006):1145-1154.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
EmotionalSpeech_IEEE(557KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Tao, JH]的文章
[Kang, YG]的文章
[Li, AJ]的文章
百度学术
百度学术中相似的文章
[Tao, JH]的文章
[Kang, YG]的文章
[Li, AJ]的文章
必应学术
必应学术中相似的文章
[Tao, JH]的文章
[Kang, YG]的文章
[Li, AJ]的文章
相关权益政策
暂无数据
收藏/分享
文件名: EmotionalSpeech_IEEETransASLP06.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。