Search Results for author:
Found 2 papers, 0 papers with code
The CORAL++ Algorithm for Unsupervised Domain Adaptation of Speaker Recogntion
To alleviate the degradation caused by domain mismatch, we propose a new feature-based unsupervised domain adaptation algorithm.
Essence Knowledge Distillation for Speech Recognition
When the student model is trained together with the correct labels and the essence knowledge from the teacher model, it not only significantly outperforms another single model with the same architecture that is trained only with the correct labels, but also consistently outperforms the teacher model that is used to generate the soft labels.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
