![On Scaling Contrastive Representations for Low-Resource Speech Recognition](https://cdn.prod.website-files.com/630dd36d5e4ce761cf292f06/656cc322e88deb5526a99cbb_Humanizing%20AI%20(380%20x%20304%20px)%20(13).jpg)
Research
On Scaling Contrastive Representations for Low-Resource Speech Recognition
![On Scaling Contrastive Representations for Low-Resource Speech Recognition](https://cdn.prod.website-files.com/630dd36d5e4ce761cf292f06/656cc322e88deb5526a99cbb_Humanizing%20AI%20(380%20x%20304%20px)%20(13).jpg)
Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are computationally expensive since they require pre-training followed by fine-tuning in a large parameter space. We explore the performance of such systems without fine-tuning by training a state-of-the-art speech recognizer on the fixed representations from the computationally demanding wav2vec 2.0 framework. We find performance to decrease without fine-tuning and, in the extreme low-resource setting, wav2vec 2.0 is inferior to its predecessor. In addition, we find that wav2vec 2.0 representations live in a low dimensional subspace and that decorrelating the features of the representations can stabilize training of the automatic speech recognizer. Finally, we propose a bidirectional extension to the original wav2vec framework that consistently improves performance.