Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 2)

The system is for track1 alone. We trained an antoencoder using unsupervised bottleneck features with word-pair information from unsupervised term detection (UTD) only on the give ENGLISH corpus. 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.