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

TL;DR

This paper introduces Conformer-1, a large-scale semi-supervised ASR model trained on 570k hours of speech data, achieving significant WER reductions and enhanced noise robustness through pseudo-labeling of public data.

Contribution

The paper demonstrates the effectiveness of large-scale semi-supervised training with pseudo-labels for improving ASR accuracy and robustness to noise.

Findings

11.5% relative WER reduction in asynchronous models

24.3% relative WER reduction in realtime models

Enhanced robustness to background noise

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% for our asynchronous and realtime models, respectively. Additionally, the model is more robust to background noise owing to the addition of these data. The results obtained in this study demonstrate that the incorporation of pseudo-labeled publicly available data is a highly effective strategy for improving ASR accuracy and noise robustness.