Using Hidden Markov Models for speech synthesis

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F99%3A00041854" target="_blank" >RIV/49777513:23520/99:00041854 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Using Hidden Markov Models for speech synthesis

Original language description

The usage of multiple Hidden Markov Models (HMMs) to prepare a Czech acoustic unit inventory and speech synthesis based on this inventory are presented in this paper. HMMs are used to model triphones. The states of triphone HMMs are automatically clustered down using binary decision trees. The clustered states are then used to automatically segment the speech corpus and to create a speech segment database. The acoustic unit inventory constructed in this way is assumed to enable more precise context modeling than was previously possible. Several speech synthesis techniques are discussed to construct a concatenation-based synthesizer. In the end, a Czech text-to-speech (TTS) system is presented.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/VS97159" target="_blank" >VS97159: Center for research in the field of cybernetic systems</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

1999

Confidentiality

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

Book/collection name

Using Hidden Markov Models for speech synthesis

ISBN

8070833394

Number of pages of the result

4

Pages from-to

—

Number of pages of the book

—

Publisher name

Technická univerzita

Place of publication

Liberec

UT code for WoS chapter

—