Open AccessStudy on the consistency analysis between the prosody and the spectrum for Mandarin speech
Author(s) -
Yeh ChengYu,
Chen KuanLin,
Hwang ShawHwa,
Yan LongJhe
Publication year - 2013
Publication title -
iet signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.384
H-Index - 42
ISSN - 1751-9683
DOI - 10.1049/iet-spr.2012.0099
Subject(s) - prosody , speech recognition , hidden markov model , mandarin chinese , consistency (knowledge bases) , syllable , computer science , speech synthesis , artificial intelligence , pronunciation , mathematics , linguistics , philosophy
In this work, a consistency analysis between the prosody and the spectrum for Mandarin speech is presented. Found by an inspection on the pronunciation process of human beings, the consistency can be interpreted as a close correlated relation of a warping curve between the spectrum and the prosody intra a syllable. Through three steps in the procedure of the consistency analysis, the hidden Markov model (HMM) algorithm is used firstly to decode HMM‐state sequences within a syllable at the same time as to divide them into three segments. Secondly, based on a designated syllable, the vector quantisation (VQ) with the Linde–Buzo–Gray algorithm is used to train the VQ codebooks of each segment. Thirdly, the prosodic vector of each segment is encoded as an index by VQ codebooks, and then the probability of each possible path is evaluated as a prerequisite to analyse the consistency. It is demonstrated experimentally that a consistency is definitely acquired in case the syllable is located exactly in the same word. These results offer a research direction that the warping process between the spectrum and the prosody intra a syllable must be considered in a text‐to‐speech system to improve the speech quality.