BUT/Phonexia Bottleneck Feature Extractor

Anna Silnova, Pavel Matejka, Ondrej Glembek, Oldrich Plchot, Ondrej Novotny, Frantisek Grezl, Petr Schwarz, Lukas Burget, Jan Cernocky


This paper complements the public release of the BUT/Phonexia bottleneck (BN) feature extractor. Starting with a brief history of Neural Network (NN)-based and BN-based approaches to speech feature extraction, it describes the structure of the released software. It follows by describing the three provided NNs: the first two trained on the US English Fisher corpus with monophone-state and tied-state targets, and the third network trained in a multi-lingual fashion on 17 Babel languages. The NNs were technically trained to classify acoustic units, however the networks were optimized with respect to the language recognition task, which is the main focus of this paper. Nevertheless, it is worth noting that apart from language recognition, the provided software can be used with any speech-related task. The paper concludes with a comprehensive summary of the results obtained on the NIST 2015 and 2017 Language Recognition Evaluations tasks.


 DOI: 10.21437/Odyssey.2018-40

Cite as: Silnova, A., Matejka, P., Glembek, O., Plchot, O., Novotny, O., Grezl, F., Schwarz, P., Burget, L., Cernocky, J. (2018) BUT/Phonexia Bottleneck Feature Extractor . Proc. Odyssey 2018 The Speaker and Language Recognition Workshop, 283-287, DOI: 10.21437/Odyssey.2018-40.


@inproceedings{Silnova2018,
  author={Anna Silnova and Pavel Matejka and Ondrej Glembek and Oldrich Plchot and Ondrej Novotny and Frantisek Grezl and Petr Schwarz and Lukas Burget and Jan Cernocky},
  title={BUT/Phonexia Bottleneck Feature Extractor	},
  year=2018,
  booktitle={Proc. Odyssey 2018 The Speaker and Language Recognition Workshop},
  pages={283--287},
  doi={10.21437/Odyssey.2018-40},
  url={http://dx.doi.org/10.21437/Odyssey.2018-40}
}