Automatic Text-Independent Artifact Detection, Localization, and Classification in the Synthetic Speech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932708" target="_blank" >RIV/49777513:23520/17:43932708 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.radioeng.cz/fulltexts/2017/17_04_1151_1160.pdf" target="_blank" >https://www.radioeng.cz/fulltexts/2017/17_04_1151_1160.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13164/re.2017.1151" target="_blank" >10.13164/re.2017.1151</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Text-Independent Artifact Detection, Localization, and Classification in the Synthetic Speech

Popis výsledku v původním jazyce

The paper describes an experiment with statistical approaches to automatic detection, localization, and classification of the basic types of artifacts in the synthetic speech produced by the Czech text-to-speech system using the unit selection method. The aim of the first experiment is to detect the artifacts by the analysis of variances (ANOVA) and hypothesis testing. The second experiment is focused on localization of the detected artifacts by the Gaussian mixture models (GMM). Finally, the developed open-set artifact classifier is described. The influence of the length of the feature vector and its composition on the resulting artifact detection accuracy is also analyzed together with other factors affecting the stability of the artifact detection process. Further investigations have shown a relatively great influence of the number of mixtures and the type of a covariance matrix on the output artifact classification error rate as well as on the computational complexity. Results of the performed experiments confirm the functionality of the proposed artifact detector based on the ANOVA and hypothesis tests, and the GMM-based artifact localizer and classifier. The described statistical approaches represent the alternatives to the standard listening tests and the manual labeling of the artifacts.

Název v anglickém jazyce

Automatic Text-Independent Artifact Detection, Localization, and Classification in the Synthetic Speech

Popis výsledku anglicky

The paper describes an experiment with statistical approaches to automatic detection, localization, and classification of the basic types of artifacts in the synthetic speech produced by the Czech text-to-speech system using the unit selection method. The aim of the first experiment is to detect the artifacts by the analysis of variances (ANOVA) and hypothesis testing. The second experiment is focused on localization of the detected artifacts by the Gaussian mixture models (GMM). Finally, the developed open-set artifact classifier is described. The influence of the length of the feature vector and its composition on the resulting artifact detection accuracy is also analyzed together with other factors affecting the stability of the artifact detection process. Further investigations have shown a relatively great influence of the number of mixtures and the type of a covariance matrix on the output artifact classification error rate as well as on the computational complexity. Results of the performed experiments confirm the functionality of the proposed artifact detector based on the ANOVA and hypothesis tests, and the GMM-based artifact localizer and classifier. The described statistical approaches represent the alternatives to the standard listening tests and the manual labeling of the artifacts.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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

2017

Kód důvěrnosti údajů

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

Název periodika

Radioengineering

ISSN

1210-2512

e-ISSN

—

Svazek periodika

26

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

10

Strana od-do

1151-1160

Kód UT WoS článku

000423270000032

EID výsledku v databázi Scopus

2-s2.0-85038078461