There is a newer version of this record available.

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


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Yougen Yuan</dc:creator>
  <dc:creator>Cheung-Chi Leung</dc:creator>
  <dc:creator>Lei Xie</dc:creator>
  <dc:creator>Hongjie Chen</dc:creator>
  <dc:creator>Bin Ma</dc:creator>
  <dc:creator>Haizhou Li</dc:creator>
  <dc:date>2017-06-15</dc:date>
  <dc:description>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.</dc:description>
  <dc:identifier>https://zenodo.org/record/814376</dc:identifier>
  <dc:identifier>10.5281/zenodo.814376</dc:identifier>
  <dc:identifier>oai:zenodo.org:814376</dc:identifier>
  <dc:relation>doi:10.5281/zenodo.809196</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/zerospeech2017</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>http://creativecommons.org/licenses/by-sa/4.0/legalcode</dc:rights>
  <dc:subject>pairwise learning</dc:subject>
  <dc:subject>zero-resource</dc:subject>
  <dc:subject>unsupervised bottleneck features</dc:subject>
  <dc:subject>neural networks</dc:subject>
  <dc:subject>autoencoder</dc:subject>
  <dc:title>Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)</dc:title>
  <dc:type>info:eu-repo/semantics/other</dc:type>
  <dc:type>dataset</dc:type>
</oai_dc:dc>
55
5
views
downloads
All versions This version
Views 558
Downloads 50
Data volume 40.7 GB0 Bytes
Unique views 508
Unique downloads 30

Share

Cite as