Published June 20, 2017
| Version v1
Dataset
Open
Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 3)
- 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) 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.
Files
Files
(8.7 GB)
Name | Size | Download all |
---|---|---|
md5:3f69162afedcfaed7d7254ccd70b2d62
|
8.7 GB | Download |