Multi-Task Transformer with Adaptive Cross-Entropy Loss for Multi-Dialect Speech Recognition

At present, most multi-dialect speech recognition models are based on a hard-parameter-sharing multi-task structure, which makes it difficult to reveal how one task contributes to others. In addition, in order to balance multi-task learning, the weights of the multi-task objective function need to b...

Full description

Bibliographic Details
Main Authors: Zhengjia Dan, Yue Zhao, Xiaojun Bi, Licheng Wu, Qiang Ji
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/24/10/1429