2 papers
eess.AS2020
Online Automatic Speech Recognition with Listen, Attend and Spell Model
Roger Hsiao, Dogan Can, Tim Ng +2
The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this pa…
eess.AS2020
Improving Language Identification for Multilingual Speakers
Andrew Titus, Jan Silovsky, Nanxin Chen +3
Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even di…