Publications
Detail of publication
Citation
2015. : Detection of Artefacts in Czech Synthetic Speech Based on ANOVA Statistics . 38th International Conference on Telecommunications and Signal Processing (TSP 2015),
Additional information
Abstract
The paper describes an experiment with using the statistical approach based on analysis of variances (ANOVA) and hypothesis tests for detection of artefacts in the synthetic speech produced by the Czech text-to-speech system employing the unit selection principle. In addition, the paper analyses influence of different speech spectral features and supra-segmental parameters as well as the length of the feature vector on the resulting artefact detection accuracy. Other factors which can also have influence on stability of the artefact detection process are analysed, too. Obtained results of performed experiments confirm that the chosen concept works properly and the presented artefact detector can be used as an alternative to the standard listening tests.
Detail of publication
Title: | Detection of Artefacts in Czech Synthetic Speech Based on ANOVA Statistics |
---|---|
Author: | Přibil, J ; Přibilová, A ; Matoušek, J. |
Language: | English |
Date of publication: | 9 Jun 2015 |
Year: | 2015 |
Type of publication: | Papers in proceedings of reviewed conferences |
Book title: | 38th International Conference on Telecommunications and Signal Processing (TSP 2015) |
DOI: | 10.1109/TSP.2015.7296377 |
ISBN: | 978-1-4799-8498-5 |
Date: | 9 Jun 2015 - 11 Jun 2015 |
Keywords
spectral features, prosodic parameters of speech, speech processing, statistical analysis
BibTeX
@INPROCEEDINGS{PribilJ_2015_Detectionof, author = {P\v{r}ibil, J and P\v{r}ibilov\'{a}, A and Matou\v{s}ek, J.}, title = {Detection of Artefacts in Czech Synthetic Speech Based on ANOVA Statistics}, year = {2015}, booktitle = {38th International Conference on Telecommunications and Signal Processing (TSP 2015)}, ISBN = {978-1-4799-8498-5}, doi = {10.1109/TSP.2015.7296377}, url = {http://www.kky.zcu.cz/en/publications/PribilJ_2015_Detectionof}, }