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


JSON-LD (schema.org) Export

{
  "@context": "https://schema.org/", 
  "@id": "https://doi.org/10.5281/zenodo.814566", 
  "@type": "Dataset", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Northwestern Polytechnical University", 
      "name": "Yougen Yuan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Institute for Infocomm Research", 
      "name": "Cheung-Chi Leung"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Northwestern Polytechnical University", 
      "name": "Lei Xie"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Northwestern Polytechnical University", 
      "name": "Hongjie Chen"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Institute for Infocomm Research", 
      "name": "Bin Ma"
    }, 
    {
      "@type": "Person", 
      "affiliation": "National University of Singapore", 
      "name": "Haizhou Li"
    }
  ], 
  "datePublished": "2017-06-15", 
  "description": "<p>The system is for track1 alone. \u00a0We 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.</p>", 
  "distribution": [
    {
      "@type": "DataDownload", 
      "contentUrl": "https://zenodo.org/api/files/6e572a54-81ab-4e9f-b661-dc66e84a302d/10_5281_zenodo_809197.tgz", 
      "fileFormat": "tgz"
    }, 
    {
      "@type": "DataDownload", 
      "contentUrl": "https://zenodo.org/api/files/6e572a54-81ab-4e9f-b661-dc66e84a302d/10_5281_zenodo_814566.tgz", 
      "fileFormat": "tgz"
    }
  ], 
  "identifier": "https://doi.org/10.5281/zenodo.814566", 
  "keywords": [
    "pairwise learning", 
    "zero-resource", 
    "unsupervised bottleneck features", 
    "neural networks", 
    "autoencoder"
  ], 
  "license": "http://creativecommons.org/licenses/by-sa/4.0/legalcode", 
  "name": "Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)", 
  "url": "https://zenodo.org/record/814566"
}
28
0
views
downloads
All versions This version
Views 2822
Downloads 00
Data volume 0 Bytes0 Bytes
Unique views 2422
Unique downloads 00

Share

Cite as