Prosody conversion from neutral speech to emotional speech

	Prosody conversion from neutral speech to emotional speech
	Tao, JH; Kang, YG ; Li, AJ
刊名	IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
	2006-07-01
卷号	14 期号:4 页码:1145-1154
关键词	emotional speech prosody analysis speech synthesis
英文摘要	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.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Acoustics ; Engineering, Electrical & Electronic
研究领域[WOS]	Acoustics ; Engineering
关键词[WOS]	VOICE CONVERSION
收录类别	SCI
语种	英语
WOS记录号	WOS:000238709200007
公开日期	2015-12-24
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/9283]
专题	自动化研究所_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.