Multilingual Bottle-Neck Feature Learning From Untranscribed Speech For Track 1 In Zerospeech2017 (System 2 -- With Vtln)

Hongjie Chen, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou LiZenodo 2017 · DOI · OpenAlex

Abstract

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.
BibTeX
@inproceedings{chen2017multilingual,
  author = {Hongjie Chen and Cheung-Chi Leung and Lei Xie and Bin Ma and Haizhou Li},
  title = {{Multilingual Bottle-Neck Feature Learning From Untranscribed Speech For Track 1 In Zerospeech2017 (System 2 -- With Vtln)}},
  booktitle = {Zenodo},
  year = {2017},
  doi = {10.5281/zenodo.822736},
}

Loading related content...

Figure