Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping
This addresses the problem of ASR accuracy and noise robustness for speech recognition applications, but it is incremental as it builds on existing semi-supervised methods.
The paper tackles improving Automatic Speech Recognition (ASR) accuracy and noise robustness by training a model on 570k hours of speech data, 91% from public sources, using Noisy Student Training with pseudo-labels, resulting in relative Word Error Rate reductions of 11.5% and 24.3% for different models.
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.