Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction
This work addresses speech recognition efficiency by reducing the need for large labeled datasets, though it is incremental as it builds on existing pre-training and masking techniques.
The paper tackles the problem of improving speech recognition by pre-training bidirectional speech encoders using a masked reconstruction loss on unlabeled data, then fine-tuning on supervised data, achieving promising results on LibriSpeech and Wall Street Journal corpora.
We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The pre-trained networks can then be fine-tuned on a smaller amount of supervised data for speech recognition. Experiments with this approach on the LibriSpeech and Wall Street Journal corpora show promising results. We find that the main factors that lead to speech recognition improvements are: masking segments of sufficient width in both time and frequency, pre-training on a much larger amount of unlabeled data than the labeled data, and domain adaptation when the unlabeled and labeled data come from different domains. The gain from pre-training is additive to that of supervised data augmentation.