An Unsupervised Autoregressive Model for Speech Representation Learning
This work addresses the need for versatile speech representations for various downstream tasks, offering an incremental advance by combining unsupervised learning with autoregressive modeling.
The paper tackles the problem of learning generic speech representations without labeled data, proposing an unsupervised autoregressive model that improves phone classification and speaker verification performance over existing methods.
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over the surface features and other supervised and unsupervised approaches. Further analysis shows that different levels of speech information are captured by our model at different layers. In particular, the lower layers tend to be more discriminative for speakers, while the upper layers provide more phonetic content.