CBA training, a two-stage adaptive ASR training scheme using a MinMax-IBF sample-complexity policy, improves WER/CER over WeNet Conformer with SpecAugment on LibriSpeech 100h and AISHELL-1.
It introduces feature domain time masking and fre- quency masking to data augmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Complexity boosted adaptive training for better low resource ASR performance
CBA training, a two-stage adaptive ASR training scheme using a MinMax-IBF sample-complexity policy, improves WER/CER over WeNet Conformer with SpecAugment on LibriSpeech 100h and AISHELL-1.