Pairwise Learning Using Unsupervised Bottleneck Features For Zero-Resource Speech Challenge 2017 (System 3)

Yougen Yuan, Cheung-Chi Leung, Lei Xie, Hongjie Chen, Bin Ma, Haizhou LiZenodo 2017 · DOI · OpenAlex

Abstract

The system is for track1 alone. We trained an antoencoder using unsupervised bottleneck features with word-pair information from unsupervised term detection (UTD) on all corpora of five languages. The unsupervised bottleneck features was extracted from an extractor of multi-task learning deep neural networks (MTL-DNN). The word-pair was found by UTD. The UTD process was built on ZRTools. The final features are obtained from the third layer in our pairwise trained autoencoder.
BibTeX
@inproceedings{yuan2017pairwise,
  author = {Yougen Yuan and Cheung-Chi Leung and Lei Xie and Hongjie Chen and Bin Ma and Haizhou Li},
  title = {{Pairwise Learning Using Unsupervised Bottleneck Features For Zero-Resource Speech Challenge 2017 (System 3)}},
  booktitle = {Zenodo},
  year = {2017},
  doi = {10.5281/zenodo.814335},
}

Loading related content...

Figure