Publication Details

Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages

KARAFIÁT Martin, BASKAR Murali K., VESELÝ Karel, GRÉZL František, BURGET Lukáš and ČERNOCKÝ Jan. Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages. In: Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018, pp. 5789-5793. ISBN 978-1-5386-4658-8.
Czech title
Analyýza mlutilingválního akustického modelu založeného na BLSTM pro jazyky s omezenými a bohatými zdroji
Type
conference paper
Language
english
Authors
URL
Keywords
Automatic speech recognition, Multilingual neural networks, Bidirectional Long Short Term Memory
Abstract
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.
Published
2018
Pages
5789-5793
Proceedings
Proceedings of ICASSP 2018
Conference
IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, CA
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Calgary, CA
DOI
BibTeX
@INPROCEEDINGS{FITPUB11720,
   author = "Martin Karafi\'{a}t and K. Murali Baskar and Karel Vesel\'{y} and Franti\v{s}ek Gr\'{e}zl and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages",
   pages = "5789--5793",
   booktitle = "Proceedings of ICASSP 2018",
   year = 2018,
   location = "Calgary, CA",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-5386-4658-8",
   doi = "10.1109/ICASSP.2018.8462083",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11720"
}
Back to top