Published June 15, 2017
| Version v1
Dataset
Open
Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 2)
Authors/Creators
- 1. Northwestern Polytechnical University
- 2. Institute for Infocomm Research
- 3. National University of Singapore
Description
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.
Files
Files
(7.8 GB)
| Name | Size | |
|---|---|---|
|
md5:c3f46ae5014b31aae0bfd24c6c92b271
|
7.8 GB | Download |