Pretraining Enhanced RNN Transducer
Recurrent neural network transducer (RNN-T) is an important branch of current end-to-end automatic speech recognition (ASR). Various promising approaches have been designed for boosting RNN-T architecture; however, few studies exploit the effectiveness of pretrained methods in this framework. In thi...
Guardat en:
| Autors principals: | , , , , , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
Tsinghua University Press
2024-12-01
|
| Col·lecció: | CAAI Artificial Intelligence Research |
| Matèries: | |
| Accés en línia: | https://www.sciopen.com/article/10.26599/AIR.2024.9150039 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|