Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43956397" target="_blank" >RIV/49777513:23520/19:43956397 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-27947-9_22" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-27947-9_22</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-27947-9_22" target="_blank" >10.1007/978-3-030-27947-9_22</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States

Popis výsledku v původním jazyce

The paper describes a system for automatic evaluation of synthetic speech quality based on continuous detection of emotional states throughout the spoken sentence using a Gaussian mixture model (GMM) classification. The final evaluation decision is made by statistical analysis of the results of emotional class differences between the sentences of original male or female voices and the speech synthesized by various methods with different parameters, approaches to prosody manipulation, etc. The basic experiments confirm the functionality of the developed system producing results comparable with those obtained by the standard listening test method. Additional investigations have shown that a number of mixtures, types of speech features, and a speech database used for creation and training of GMMs have a relatively great influence on continuous emotional style detection and the final quality evaluation of the tested synthetic speech.

Název v anglickém jazyce

Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States

Popis výsledku anglicky

The paper describes a system for automatic evaluation of synthetic speech quality based on continuous detection of emotional states throughout the spoken sentence using a Gaussian mixture model (GMM) classification. The final evaluation decision is made by statistical analysis of the results of emotional class differences between the sentences of original male or female voices and the speech synthesized by various methods with different parameters, approaches to prosody manipulation, etc. The basic experiments confirm the functionality of the developed system producing results comparable with those obtained by the standard listening test method. Additional investigations have shown that a number of mixtures, types of speech features, and a speech database used for creation and training of GMMs have a relatively great influence on continuous emotional style detection and the final quality evaluation of the tested synthetic speech.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech, and Dialogue 22nd International Conference, TSD 2019, Ljubljana,Slovenia, September 11-13, 2019, Proceedings

ISBN

978-3-030-27946-2

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

10

Strana od-do

264-273

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Ljubljana, Slovenia

Datum konání akce

11. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—