Dataset Open Access

Multilingual bottle-neck feature learning from untranscribed speech for track 1 in zerospeech2017 (system 2 -- with VTLN)

Hongjie Chen Chen; Cheung-Chi Leung; Lei Xie; 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>Hongjie Chen Chen</dc:creator>
  <dc:creator>Cheung-Chi Leung</dc:creator>
  <dc:creator>Lei Xie</dc:creator>
  <dc:creator>Bin Ma</dc:creator>
  <dc:creator>Haizhou Li</dc:creator>
  <dc:date>2017-07-04</dc:date>
  <dc:description>We investigate the extraction of bottle-neck features (BNFs) for multiple languages without access to manual transcription. Multilingual BNFs are derived from a multi-task learning deep neural network which is trained with unsupervised phoneme-like labels. The unsupervised phoneme-like labels are obtained from language-dependent Dirichlet process Gaussian mixture models separately trained on untranscribed speech of multiple languages.


In this version, the input MFCC for DPGMM is processed with VTLN.


 </dc:description>
  <dc:identifier>https://zenodo.org/record/822737</dc:identifier>
  <dc:identifier>10.5281/zenodo.822737</dc:identifier>
  <dc:identifier>oai:zenodo.org:822737</dc:identifier>
  <dc:relation>doi:10.5281/zenodo.822736</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/4.0/legalcode</dc:rights>
  <dc:title>Multilingual bottle-neck feature learning from untranscribed speech for track 1 in zerospeech2017 (system 2 -- with VTLN)</dc:title>
  <dc:type>info:eu-repo/semantics/other</dc:type>
  <dc:type>dataset</dc:type>
</oai_dc:dc>
97
29
views
downloads
All versions This version
Views 9797
Downloads 2929
Data volume 233.1 GB233.1 GB
Unique views 9494
Unique downloads 2424

Share

Cite as