Advanced Search
Japanese | English

naistar (NAIST Academic Repository) >
学術リポジトリ naistar / NAIST Academic Repository naistar >
国際会議発表論文 / Proceedings >
情報科学研究科 / Graduate School of Information Science >

Please use this identifier to cite or link to this item:

Title: A Trainable Excitation Model for HMM-Based Speech Synthesis
Authors: Ranniery Maia
Tomoki Toda
Heiga. Zen
Yoshihiko Nankaku
Keiichi Tokuda
Keywords: speech processing
speech synthesis
Issue Date: Aug-2007
Start page: 1909
End page: 1912
Abstract: This paper introduces a novel excitation approach for speech synthesizers in which the final waveform is generated through parameters directly obtained from Hidden Markov Models (HMMs). Despite the attractiveness of the HMM-based speech synthesis technique, namely utilization of small corpora and flexibility concerning the achievement of different voice styles, synthesized speech presents a characteristic buzziness caused by the simple excitation model which is employed during the speech production. This paper presents an innovative scheme where mixed excitation is modeled through closed-loop training of a set of state-dependent filters and pulse trains, with minimization of the error between excitation and residual sequences. The proposed method shows effectiveness, yielding synthesized speech with quality far superior to the simple excitation baseline and comparable to the best excitation schemes thus far reported for HMM-based speech synthesis.
Description: INTERSPEECH2007: 8th Annual Conference of the International Speech Communication Association, August 27-31, 2007, Antwerp, Belgium.
Rights: Copyright 2007 ISCA
Text Version: Publisher
Appears in Collections:情報科学研究科 / Graduate School of Information Science

Files in This Item:

File SizeFormat
INTERSPEECH_2007_1909.pdf706.28 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Copyright (c) 2007-2012 Nara Institute of Science and Technology All Rights Reserved.
DSpace Software Copyright © 2002-2010  Duraspace - Feedback