This paper introduces a novel Token-and-Duration Transducer (TDT)
archit...
In this paper, we extend previous self-supervised approaches for languag...
This paper proposes a modification to RNN-Transducer (RNN-T) models for
...
We present AmberNet, a compact end-to-end neural network for Spoken Lang...
Designing data sharing mechanisms providing performance and strong priva...
We present MarbleNet, an end-to-end neural network for Voice Activity
De...