Search Results for author:
Found 4 papers, 1 papers with code
Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models
As this performance is close to our supervised baseline of 0. 94% EER, this contribution is a step towards supervised performance on SV with SSL.
Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations
Implementing these two modifications to SimCLR improves performance and results in 7. 85% EER on VoxCeleb1-O, outperforming other equivalent methods.
Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data.
A benchmark for toxic comment classification on Civil Comments dataset
BiLSTM remains a good compromise between performance and inference time.
Ranked #1 on
Toxic Comment Classification
on Civil Comments
