While standard speaker diarization attempts to answer the question "who
...
We introduce a multilingual speaker change detection model (USM-SCD) tha...
In this work we propose a novel token-based training strategy that impro...
In this paper, we present a novel approach to adapt a sequence-to-sequen...
While recent research advances in speaker diarization mostly focus on
im...
Automated speech recognition coverage of the world's languages continues...
This paper reviews the collective endeavors by the team of authors in
ex...
In this work, we investigate the possibility of replacing the ℓ_2 loss
w...