Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published June 15, 2017 | Version v1
Dataset Open

Multilingual Bottle-Neck Feature Learning from Untranscribed data for track 1 in zerospeech2017 (system 1 -- without VTLN)

  • 1. Northwestern Polytechnical University, China
  • 2. Institute for Infocomm Research, A*STAR, Singapore
  • 3. National University of Singapore, Singapore

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.

Files

Files (7.8 GB)

Name Size Download all
md5:384d7ae79e1e64f41de06f8d6c99089a
7.8 GB Download