Conference paper

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.
Publication language:english
Original title:Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages
Title (cs):Analyýza mlutilingválního akustického modelu založeného na BLSTM pro jazyky s omezenými a bohatými zdroji
Pages:5789-5793
Proceedings:Proceedings of ICASSP 2018
Conference:2018 IEEE International Conference on Acoustics, Speech and Signal Processing
Place:Calgary, CA
Year:2018
ISBN:978-1-5386-4658-8
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2018/karafiat_icassp2018_0005789.pdf [PDF]
Keywords
Automatic speech recognition, Multilingual neural networks, Bidirectional Long Short Term Memory
Annotation
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.
BibTeX:
@INPROCEEDINGS{
   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},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11720}
}

Your IPv4 address: 54.156.51.193
Switch to IPv6 connection

DNSSEC [dnssec]