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

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.

 

Files (8.0 GB)
Name Size
10_5281_zenodo_822737.tar.gz
md5:aec84d688de278e3ed8df99fc536db68
8.0 GB Download
175
35
views
downloads
All versions This version
Views 175175
Downloads 3535
Data volume 281.3 GB281.3 GB
Unique views 168168
Unique downloads 3030

Share

Cite as