LAUSR

Spelling-Aware Word-Based End-to-End ASR

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2022.3192199

Abstract: We propose a new end-to-end architecture for automatic speech recognition that expands the “listen, attend and spell” (LAS) paradigm. While the main word-predicting network is trained to predict words, the secondary, speller network, is optimized… read more here.

Keywords: end end; aware word; word based; word ... See more keywords