research data . Dataset . 2017

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

Yougen Yuan; Cheung-Chi Leung; Xie, Lei; Hongjie Chen; Ma, Bin; Haizhou Li;
Open Access
  • Published: 15 Jun 2017
  • Publisher: Zenodo
Abstract
<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). 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>
Subjects
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: pairwise learning, zero-resource, unsupervised bottleneck features, neural networks, autoencoder
Download fromView all 7 versions
Zenodo
Dataset . 2017
Provider: Zenodo
Zenodo
Dataset . 2017
Provider: Zenodo
Zenodo
Dataset . 2017
Provider: Datacite
Zenodo
Dataset . 2017
Provider: Zenodo
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue