An Unsupervised Autoregressive Model for Speech Representation Learning

Yu-An Chung, Wei-Ning Hsu, Hao Tang, James Glass


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.


 DOI: 10.21437/Interspeech.2019-1473

Cite as: Chung, Y., Hsu, W., Tang, H., Glass, J. (2019) An Unsupervised Autoregressive Model for Speech Representation Learning. Proc. Interspeech 2019, 146-150, DOI: 10.21437/Interspeech.2019-1473.


@inproceedings{Chung2019,
  author={Yu-An Chung and Wei-Ning Hsu and Hao Tang and James Glass},
  title={{An Unsupervised Autoregressive Model for Speech Representation Learning}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={146--150},
  doi={10.21437/Interspeech.2019-1473},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1473}
}