Feature Disentanglement - I
How deep learning models can isolate independent factors of variation in data through VAEs and Beta-TCVAE, enabling controlled synthesis and better downstream representations.
#speech representation
Content tagged with "speech representation"
Learning Speaker Representation with Semi-supervised Learning Approach for Speaker Profiling
A semi-supervised framework for speaker profiling that leverages external unlabelled corpora via supervised, unsupervised, and consistency training, achieving RMSE of 6.8 years on age estimation.