sorry, we can't preview this file
...but you can still download 10_5281_zenodo_808915.tar.gz
Multilingual Bottle-Neck Feature Learning from Untranscribed data for track 1 in zerospeech2017 (system 1 -- without VTLN)
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
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.