Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping

arXiv:2404.07341v1 Announce Type: cross
Abstract: This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we perform Noisy Student Training after generating pseudo-labels for the unlabeled public data using a strong Conformer RNN-T baseline model. The addition of these pseudo-labeled data results in remarkable improvements in relative Word Error Rate (WER) by 11.5% and 24.3% …

abstract acquired arxiv asr audio automatic speech recognition bootstrapping cs.cl cs.lg cs.sd data dataset eess.as labels paper public public data recognition robust scale speech speech recognition training type via