activity
20152023
most citedMACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2023

ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging

Fangyuan Wang, Ming Hao, Yuhai Shi +1

The conventional recipe for Automatic Speech Recognition (ASR) models is to 1) train multiple checkpoints on a training set while relying on a validation set to prevent overfitting…