First Steps Towards Hybrid Speech Synthesis in Czech TTS System ARTIC

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952755" target="_blank" >RIV/49777513:23520/18:43952755 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_69" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_69</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-99579-3_69" target="_blank" >10.1007/978-3-319-99579-3_69</a>

Jazyk výsledku

angličtina

Název v původním jazyce

First Steps Towards Hybrid Speech Synthesis in Czech TTS System ARTIC

Popis výsledku v původním jazyce

The hybrid speech synthesis, combining an HMM-based parameter trajectories generator and unit selection, was reported to achieve high speech output quality, in some cases even outperforming the “classic” unit selection method, while having reasonable cost of hardware requirements increase, especially when compared to modern DNN-based (e.g. WaveNet) speech synthesis methods. The present paper introduces one of this hybrid approaches, facing up the mismatch between rather smooth flow of parameters when generated by a model and between their varying evolution when obtained from speech. We also describe several modifications of target cost computation, influencing the selection of units being close to the required parameters, while our aim is to obtain a notion of the mutual interactions within the modified selection process. The overall conclusion is covered by listening tests, showing comparable quality of the trial hybrid synthesis described to unit selection method tuned through the years.

Název v anglickém jazyce

First Steps Towards Hybrid Speech Synthesis in Czech TTS System ARTIC

Popis výsledku anglicky

The hybrid speech synthesis, combining an HMM-based parameter trajectories generator and unit selection, was reported to achieve high speech output quality, in some cases even outperforming the “classic” unit selection method, while having reasonable cost of hardware requirements increase, especially when compared to modern DNN-based (e.g. WaveNet) speech synthesis methods. The present paper introduces one of this hybrid approaches, facing up the mismatch between rather smooth flow of parameters when generated by a model and between their varying evolution when obtained from speech. We also describe several modifications of target cost computation, influencing the selection of units being close to the required parameters, while our aim is to obtain a notion of the mutual interactions within the modified selection process. The overall conclusion is covered by listening tests, showing comparable quality of the trial hybrid synthesis described to unit selection method tuned through the years.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GA16-04420S" target="_blank" >GA16-04420S: Kombinované využití fonetických a korpusově založených postupů při odstraňování rušivých jevů v řečové syntéze</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Speech and Computer 20th International Conference, SPECOM 2018 Leipzig, Germany, September 18–22, 2018, Proceedings

ISBN

978-3-319-99578-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

11

Strana od-do

676-686

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

Leipzig, Germany

Datum konání akce

18. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—