Generation of creaky voice for improving the quality of HMM-based speech synthesis

详细信息    查看全文

• 作者：N.P. Narendra ; ^{narendrasince1987@gmail.com} ; K. Sreenivasa Rao ^{ksrao@iitkgp.ac.in}
• 关键词：HMM-based speech synthesis ; Detection of creaky voice ; Zero-frequency filtering ; Epoch parameters ; Synthesis of creaky voice ; Deterministic plus noise model ; Hybrid source modelling
• 刊名：Computer Speech & Language
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：42
• 期：Complete
• 页码：38-58
• 全文大小：1078 K
• 卷排序：42

文摘

An HMM-based speech synthesis system capable of generating creaky voice is developed. Two main issues involved in the synthesis of creaky voice are addressed. A creaky voice detection method is proposed based on the analysis of variation of epoch parameters for different voicing regions. A hybrid source model which is an extension of recently developed time-domain deterministic plus noise model is proposed for modelling creaky excitation signal.