標題: A New Model-based Prosody Coder for Mandarin Speech
作者: Chiang, Chen-Yu
Hung, Yu-Ping
Chen, Sin-Horng
Wang, Yih-Ru
電機工程學系
Department of Electrical and Computer Engineering
關鍵字: Prosody coding;Prosodic model
公開日期: 2013
摘要: In this paper, a novel parametric prosody coding approach for Mandarin speech is proposed. It employs a hierarchical prosodic model (HPM) as a prosody generating model in the encoder to analyze the speech prosody of the input utterance to obtain a parametric representation of four prosodic-acoustic features of syllable pitch contour, syllable duration, syllable energy level, and syllable-juncture pause duration for encoding. In the decoder, the four prosodic-acoustic features are reconstructed by a synthesis operation using the decoded HPM parameters. The reconstructed prosodic features are lastly used in an HMM-based speech synthesizer to help to generate the reconstructed speech. Experimental results show that the reconstructed speech has good quality at low data rates of 114.9 bits/s for a speaker-dependent task. An informal listening test confirmed decoded speeches sounded very fluently.
URI: http://dx.doi.org/10.1109/IIH-MSP.2013.24
http://hdl.handle.net/11536/135358
ISBN: 978-0-7695-5120-3
DOI: 10.1109/IIH-MSP.2013.24
期刊: 2013 NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING (IIH-MSP 2013)
起始頁: 60
結束頁: 63
Appears in Collections:Conferences Paper