Adaptive Feature Selection for End-to-End Speech Translation

EMNLP, pp. 2533-2544, 2020.

Cited by: 0|Bibtex|Views11|Links
EI

Abstract:

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we propose adaptive feature selection (AFS) for encoder-decoder based E2E ST. We first pre-train an ASR encoder and apply AFS to dynamically est...More

Code:

Data:

Your rating :
0

 

Tags
Comments