activity
20202025
most citedInfusing Future Information into Monotonic Attention Through Language Models

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2020

Small energy masking for improved neural network training for end-to-end speech recognition

Chanwoo Kim, Kwangyoun Kim, Sathish Reddy Indurthi

In this paper, we present a Small Energy Masking (SEM) algorithm, which masks inputs having values below a certain threshold. More specifically, a time-frequency bin is masked if t…