Hongjie Chen Chen
Cheung-Chi Leung
Lei Xie
Bin Ma
Haizhou Li
2017-07-04
<p>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.</p>
<blockquote>
<p>In this version, the input MFCC for DPGMM is processed with VTLN.</p>
</blockquote>
<p> </p>
https://doi.org/10.5281/zenodo.822737
oai:zenodo.org:822737
Zenodo
https://zenodo.org/communities/zerospeech2017
https://doi.org/10.5281/zenodo.822736
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Multilingual bottle-neck feature learning from untranscribed speech for track 1 in zerospeech2017 (system 2 -- with VTLN)
info:eu-repo/semantics/other