Automatic segmentation for Czech concatenative speech synthesis using statistical approach with boundary-specific correction

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F03%3A00000215" target="_blank" >RIV/49777513:23520/03:00000215 - isvavai.cz</a>

Alternative codes found

RIV/49777513:23520/03:00000044

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Automatic segmentation for Czech concatenative speech synthesis using statistical approach with boundary-specific correction

Original language description

This paper deals with the problems of automatic segmentation for the purposes of Czech concatenative speech synthesis. Statistical approach to speech segmentation using HMMs is applied in the baseline system. Several improvements of this system are thenproposed to get more accurate segmentation results. These enhancements mainly concern the various strategies of HMM initialization (flat-start initialization, hand-labeled or speaker independent HMM bootstrapping). Since HTK was utilized in our work, a correction of the output boundary placements is proposed to reflect speech parameterization mechanism. An objective comparison of various automatic methods and manual segmentation is performed to find out the best method. The best results were obtained for boundary-specific statistical correction of the segmentation that resulted from bootstrapping with hand-labeled HMMs (96% segmentation accuracy in tolerance region 20ms).

Czech name

Automatická segmentace pro konkatenační syntézu češtiny

Czech description

Tento článek pojednává o problému automatické segmentace pro syntézu mluvené češtiny. V úloze byl využit statistický přístup založený na skrytých Markovových modelech.

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/GP102%2F02%2FP134" target="_blank" >GP102/02/P134: Statistical approach to automatic speech segment database construction for synthesis of Czech</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2003

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Eurospeech

ISSN

1018-4074

e-ISSN

—

Volume of the periodical

2003

Issue of the periodical within the volume

—

Country of publishing house

CH - SWITZERLAND

Number of pages

4

Pages from-to

301

UT code for WoS article

—

EID of the result in the Scopus database

—