Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-Supervised Speaker Verification
In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a <italic>bootstrap equilibrium speaker representation learning</italic> in the front-end and an <italic>uncertainty-aware probabilistic speaker embedding training</italic> in the back-end. In the...
Na minha lista:
| Principais autores: | , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
IEEE
2021-01-01
|
| coleção: | IEEE Access |
| Assuntos: | |
| Acesso em linha: | https://ieeexplore.ieee.org/document/9656847/ |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|