ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM

ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM

Architecture of the multimodal text to speech synthesis system based on the voice conversion framework was proposed. Such system could be tuned to the specific speaker without any costs losses on the training phase and based on one speaker base, having in TTS system. Structural scheme for this type...

Full description

Bibliographic Details
Main Authors: V. A. Zakharyeu, A. A. Petrovsky
Format: Article
Language:Russian
Published: Educational institution «Belarusian State University of Informatics and Radioelectronics» 2019-06-01
Series:Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
Subjects:
конверсия голоса
мультиголосовой синтезатор речи по тексту
текстонезависимое обучение
скрытая марковская модель
параметрическая модель представления сигнала
Online Access:https://doklady.bsuir.by/jour/article/view/239
id doaj-2cc57912790e47f0a59555ce607ea392
record_format Article
spelling doaj-2cc57912790e47f0a59555ce607ea3922021-07-28T16:19:45ZrusEducational institution «Belarusian State University of Informatics and Radioelectronics»Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki1729-76482019-06-01075763238ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEMV. A. Zakharyeu0A. A. Petrovsky1Белорусский государственный университет информатики и радиоэлектроникиБелорусский государственный университет информатики и радиоэлектроникиArchitecture of the multimodal text to speech synthesis system based on the voice conversion framework was proposed. Such system could be tuned to the specific speaker without any costs losses on the training phase and based on one speaker base, having in TTS system. Structural scheme for this type of the speech synthesizer, with the description of the functionality of the main blocks were presented. Their specific characteristics are synergy approach to the architecture and text-independent mode in the training phase.https://doklady.bsuir.by/jour/article/view/239конверсия голосамультиголосовой синтезатор речи по текстутекстонезависимое обучениескрытая марковская модельпараметрическая модель представления сигнала
collection DOAJ
language Russian
format Article
sources DOAJ
author V. A. Zakharyeu
A. A. Petrovsky
spellingShingle V. A. Zakharyeu
A. A. Petrovsky
ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
конверсия голоса
мультиголосовой синтезатор речи по тексту
текстонезависимое обучение
скрытая марковская модель
параметрическая модель представления сигнала
author_facet V. A. Zakharyeu
A. A. Petrovsky
author_sort V. A. Zakharyeu
title ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
title_short ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
title_full ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
title_fullStr ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
title_full_unstemmed ARCHITECTURE OF THE MULTIVOICE TEXT-TO-SPEECH SYSTEM
title_sort architecture of the multivoice text-to-speech system
publisher Educational institution «Belarusian State University of Informatics and Radioelectronics»
series Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
issn 1729-7648
publishDate 2019-06-01
description Architecture of the multimodal text to speech synthesis system based on the voice conversion framework was proposed. Such system could be tuned to the specific speaker without any costs losses on the training phase and based on one speaker base, having in TTS system. Structural scheme for this type of the speech synthesizer, with the description of the functionality of the main blocks were presented. Their specific characteristics are synergy approach to the architecture and text-independent mode in the training phase.
topic конверсия голоса
мультиголосовой синтезатор речи по тексту
текстонезависимое обучение
скрытая марковская модель
параметрическая модель представления сигнала
url https://doklady.bsuir.by/jour/article/view/239
work_keys_str_mv AT vazakharyeu architectureofthemultivoicetexttospeechsystem
AT aapetrovsky architectureofthemultivoicetexttospeechsystem
_version_ 1721268039452721152

Similar Items