Semi-Supervised Learning for Automatic Speech Recognition with Word Error Rate Estimation and Targeted Domain Data Selection

There is a growing demand for leveraging untranscribed multi-domain data in semi-supervised learning (SSL) for automatic speech recognition (ASR) to broaden its applications. However, domain mismatch between source and target data can limit SSL’s performance gains, even when transcript accuracy for training is high. While word error rate (WER) estimation (WE) methods for automatic transcription have advanced, they remain insufficient for handling multi-domain data.