activity
20182024
most citedTransfer learning of language-independent end-to-end ASR with language model fusion

6 citations · 19 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023

O-1: Self-training with Oracle and 1-best Hypothesis

Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran +1

We introduce O-1, a new self-training objective to reduce training bias and unify training and evaluation metrics for speech recognition. O-1 is a faster variant of Expected Minimu…