ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

BUT 2014 Babel system: analysis of adaptation in NN based systems

Martin Karafiát, František Grézl, Karel Veselý, Mirko Hannemann, Igor Szőke, Jan Černocký

Features based on a hierarchy of neural networks with compressive layers — Stacked Bottle-Neck (SBN) features — were recently shown to provide excellent performance in LVCSR systems. This paper summarizes several techniques investigated in our work towards Babel 2014 evaluations: (1) using several versions of fundamental frequency (F0) estimates, (2) semi-supervised training on un-transcribed data and mainly (3) adapting the NN structure at different levels. They are tested on three 2014 Babel languages with full GMM- and DNN-based systems. Separately and in combination, they are shown to outperform the baselines and confirm the usefulness of bottle-neck features in current ASR systems.


doi: 10.21437/Interspeech.2014-502

Cite as: Karafiát, M., Grézl, F., Veselý, K., Hannemann, M., Szőke, I., Černocký, J. (2014) BUT 2014 Babel system: analysis of adaptation in NN based systems. Proc. Interspeech 2014, 3002-3006, doi: 10.21437/Interspeech.2014-502

@inproceedings{karafiat14_interspeech,
  author={Martin Karafiát and František Grézl and Karel Veselý and Mirko Hannemann and Igor Szőke and Jan Černocký},
  title={{BUT 2014 Babel system: analysis of adaptation in NN based systems}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={3002--3006},
  doi={10.21437/Interspeech.2014-502},
  issn={2308-457X}
}