Task #3773
closedTask #3680: RA4a - Automatic error prediction
Task #3770: Experiment with gender and age classification for synthetic speech error predictions and evaluation
Submit a paper to journal Measurement Science Review
0%
Description
Title: GMM-based Speaker Age and Gender Classification in Czech and Slovak
Abstract:
The paper describes an experiment with using the Gaussian mixture models (GMM) for automatic classification of the speaker age and gender. The paper next analyses and compares influence of different number of mixtures and different types of speech features used for GMM gender/age classification. In addition, the computational complexity dependence on the number of used mixtures is there also analysed. Finally, the GMM classification accuracy is compared with the output of the conventional listening tests. The results of these objective and subjective evaluations are in correspondence.
Submitted, waiting for decision...
No data to display