Standard

Parametric speech synthesis and user interface for speech modification. / Shipilo, A.; Barabanov, A.; Lipkovich, M.

в: Lecture Notes in Computer Science, Том 8113, 2013, стр. 249-256.

Результаты исследований: Научные публикации в периодических изданияхстатья

Harvard

APA

Vancouver

Author

Shipilo, A. ; Barabanov, A. ; Lipkovich, M. / Parametric speech synthesis and user interface for speech modification. в: Lecture Notes in Computer Science. 2013 ; Том 8113. стр. 249-256.

BibTeX

@article{0fe8878f24f149029f900cd16cfb1c48,
title = "Parametric speech synthesis and user interface for speech modification",
abstract = "A new parametric allophone-to-speech synthesis system of the Russian language is described. It is assumed that a sequence of allophones with prosodic information is given and it is required to compute the corresponding speech signal. Allophones are stored in the database by model parameter sets only. The model of a voiced signal is purely polyharmonic. Modification of pitch, energy and duration can be effectively made to a large extent without loss of quality. The system is based on precise estimation of harmonic parameters at the stage of database parameterization, on the cluster description of allophone merging in the Russian language and on the effective synthesis algorithm with opportunity to arbitrarily change any prosodic parameter through the graphic user interface. {\textcopyright} 2013 Springer International Publishing.",
author = "A. Shipilo and A. Barabanov and M. Lipkovich",
year = "2013",
doi = "10.1007/978-3-319-01931-4_33",
language = "English",
volume = "8113",
pages = "249--256",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Nature",

}

RIS

TY - JOUR

T1 - Parametric speech synthesis and user interface for speech modification

AU - Shipilo, A.

AU - Barabanov, A.

AU - Lipkovich, M.

PY - 2013

Y1 - 2013

N2 - A new parametric allophone-to-speech synthesis system of the Russian language is described. It is assumed that a sequence of allophones with prosodic information is given and it is required to compute the corresponding speech signal. Allophones are stored in the database by model parameter sets only. The model of a voiced signal is purely polyharmonic. Modification of pitch, energy and duration can be effectively made to a large extent without loss of quality. The system is based on precise estimation of harmonic parameters at the stage of database parameterization, on the cluster description of allophone merging in the Russian language and on the effective synthesis algorithm with opportunity to arbitrarily change any prosodic parameter through the graphic user interface. © 2013 Springer International Publishing.

AB - A new parametric allophone-to-speech synthesis system of the Russian language is described. It is assumed that a sequence of allophones with prosodic information is given and it is required to compute the corresponding speech signal. Allophones are stored in the database by model parameter sets only. The model of a voiced signal is purely polyharmonic. Modification of pitch, energy and duration can be effectively made to a large extent without loss of quality. The system is based on precise estimation of harmonic parameters at the stage of database parameterization, on the cluster description of allophone merging in the Russian language and on the effective synthesis algorithm with opportunity to arbitrarily change any prosodic parameter through the graphic user interface. © 2013 Springer International Publishing.

UR - http://link.springer.com/chapter/10.1007/978-3-319-01931-4_33

U2 - 10.1007/978-3-319-01931-4_33

DO - 10.1007/978-3-319-01931-4_33

M3 - Article

VL - 8113

SP - 249

EP - 256

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -

ID: 7833544