Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)

Dataset OPEN
Yougen Yuan ; Cheung-Chi Leung ; Lei Xie ; Hongjie Chen ; Bin Ma ; Haizhou Li
  • Publisher: Zenodo
  • Related identifiers: doi: 10.5281/zenodo.814376
  • Subject: autoencoder | pairwise learning | neural networks | zero-resource | unsupervised bottleneck features
    acm: ComputingMethodologies_PATTERNRECOGNITION

<p>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). ... View more
Share - Bookmark

  • Download from
    Zenodo via Zenodo (Dataset)
  • Cite this research data