Detail publikace

Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages

KARAFIÁT, M. BASKAR, M. VESELÝ, K. GRÉZL, F. BURGET, L. ČERNOCKÝ, J.

Originální název

Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

The paper provides an analysis of automatic speech recognition systems (ASR) based on multilingual BLSTM, where we used multi-task training with separate classification layer for each language. The focus is on low resource languages, where only a limited amount of transcribed speech is available. In such scenario, we found it essential to train the ASR systems in a multilingual fashion and we report superior results obtained with pre-trained multilingual BLSTM on this task. The high resource languages are also taken into account and we show the importance of language richness for multilingual training. Next, we present the performance of this technique as a function of amount of target language data. The importance of including context information into BLSTM multilingual systems is also stressed, and we report increased resilience of large NNs to overtraining in case of multi-task training.

Klíčová slova

Automatic speech recognition, Multilingual neural networks, Bidirectional Long Short Term Memory

Autoři

KARAFIÁT, M.; BASKAR, M.; VESELÝ, K.; GRÉZL, F.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

15. 4. 2018

Nakladatel

IEEE Signal Processing Society

Místo

Calgary

ISBN

978-1-5386-4658-8

Kniha

Proceedings of ICASSP 2018

Strany od

5789

Strany do

5793

Strany počet

5

URL

https://www.fit.vut.cz/research/publication/11720/

BibTex

@inproceedings{BUT155042,
  author="Martin {Karafiát} and Murali Karthick {Baskar} and Karel {Veselý} and František {Grézl} and Lukáš {Burget} and Jan {Černocký}",
  title="Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages",
  booktitle="Proceedings of ICASSP 2018",
  year="2018",
  pages="5789--5793",
  publisher="IEEE Signal Processing Society",
  address="Calgary",
  doi="10.1109/ICASSP.2018.8462083",
  isbn="978-1-5386-4658-8",
  url="https://www.fit.vut.cz/research/publication/11720/"
}