A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Improving multilingual end-to-end (E2E) automatic speech recognition (ASR) systems have manifold advantages. They simplify the training strategy, are easier to scale and exhibit better performance over monolingual models. However, it is still challenging to use a single multilingual model to recognize multiple languages without knowing the input language, as most multilingual models assume the availability of the input language. In this paper, we introduce multi-softmax model to improve thedoi:10.21437/interspeech.2021-1298 dblp:conf/interspeech/JoshiDSM0021 fatcat:7m72xcad6femxibpisgmuvxcgm