research
∙
09/15/2023
Augmenting conformers with structured state space models for online speech recognition
Online speech recognition, where the model only accesses context to the ...
share
research
∙
10/13/2022
JOIST: A Joint Speech and Text Streaming Model For ASR
We present JOIST, an algorithm to train a streaming, cascaded, encoder e...
research
∙
06/14/2021
