VoxCeleb Enrichment for Age and Gender Recognition
This work provides improved metadata for speaker recognition datasets, aiding researchers in age and gender recognition tasks, but it is incremental as it builds on existing datasets and methods.
The authors enriched the VoxCeleb dataset with age and gender labels by querying celebrity databases and applying consensus rules, and they built recognition models, achieving an F1-score of 0.9829 for gender recognition and a mean absolute error of 9.443 years for age regression.
VoxCeleb datasets are widely used in speaker recognition studies. Our work serves two purposes. First, we provide speaker age labels and (an alternative) annotation of speaker gender. Second, we demonstrate the use of this metadata by constructing age and gender recognition models with different features and classifiers. We query different celebrity databases and apply consensus rules to derive age and gender labels. We also compare the original VoxCeleb gender labels with our labels to identify records that might be mislabeled in the original VoxCeleb data. On modeling side, we design a comprehensive study of multiple features and models for recognizing gender and age. Our best system, using i-vector features, achieved an F1-score of 0.9829 for gender recognition task using logistic regression, and the lowest mean absolute error (MAE) in age regression, 9.443 years, is obtained with ridge regression. This indicates challenge in age estimation from in-the-wild style speech data.