Dataset Open Access

Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)

Yougen Yuan; Cheung-Chi Leung; Lei Xie; Hongjie Chen; Bin Ma; Haizhou Li

The system is for track1 alone.  We trained an antoencoder using unsupervised bottleneck features with word-pair information from Switchboard. The unsupervised bottleneck features was extracted from an extractor of multi-task learning deep neural networks (MTL-DNN). The word-pair information was the ground truth from Switchboard. The final features are obtained from the third layer in our pairwise trained autoencoder.

Files (16.3 GB)
Name Size
10_5281_zenodo_809197.tgz
md5:52021927048d26ac14470c972c3ffb99
8.1 GB Download
10_5281_zenodo_814566.tgz
md5:2948b438c9dcdae8e449378f260b3ce8
8.1 GB Download

Share

Cite as