Publication detail

Multilingual BLSTM and Speaker-Specific Vector Adaptation in 2016 BUT BABEL SYSTEM

KARAFIÁT, M. BASKAR, M. MATĚJKA, P. VESELÝ, K. GRÉZL, F. ČERNOCKÝ, J.

Original Title

Multilingual BLSTM and Speaker-Specific Vector Adaptation in 2016 BUT BABEL SYSTEM

Type

conference paper

Language

English

Original Abstract

This paper provides an extensive summary of BUT 2016 system for the last Babel evaluations. It concentrates on multi-lingual training of both DNN-based features and acoustic models and on the lowdimensional to speaker adaptation.

Keywords

Automatic speech recognition, Multilingual neural networks, Bidirectional Long Short Term Memory, i-vectors, Sequence Summarizing Neural Networks.

Authors

KARAFIÁT, M.; BASKAR, M.; MATĚJKA, P.; VESELÝ, K.; GRÉZL, F.; ČERNOCKÝ, J.

Released

13. 12. 2016

Publisher

IEEE Signal Processing Society

Location

San Diego

ISBN

978-1-5090-4903-5

Book

Proceedings of SLT 2016

Pages from

637

Pages to

643

Pages count

7

URL

BibTex

@inproceedings{BUT132604,
  author="Martin {Karafiát} and Murali Karthick {Baskar} and Pavel {Matějka} and Karel {Veselý} and František {Grézl} and Jan {Černocký}",
  title="Multilingual BLSTM and Speaker-Specific Vector Adaptation in 2016 BUT BABEL SYSTEM",
  booktitle="Proceedings of SLT 2016",
  year="2016",
  pages="637--643",
  publisher="IEEE Signal Processing Society",
  address="San Diego",
  doi="10.1109/SLT.2016.7846330",
  isbn="978-1-5090-4903-5",
  url="https://www.fit.vut.cz/research/publication/11310/"
}